Temporal Video Grounding

Follow this topic Ask about this topic

Temporal video grounding studies how to identify when a described action, event, or state occurs in a video, often returning one or more time intervals. Methods range from proposal-based models and cross-modal alignment to zero-shot video-language models, query-guided frame selection, and agents that search long videos in stages. Training commonly uses temporal annotations and benchmarks such as QVHighlights, Charades-STA, and ActivityNet-Captions, while newer work explores weak supervision, reinforcement learning, and open-world queries. A central challenge is that fluent answers and broad event recognition do not guarantee precise, faithful evidence localization, especially in long videos or when queries are ambiguous or match multiple moments.

Latest papers

169 papers28 papers in the last four weeks, up 115% on the four weeks before. 0.2% of all new papers.

May 2, 2026

Two-Pass Zero-Shot Temporal-Spatial Grounding of Rare Traffic Events in Surveillance Video

Grounding traffic accidents in real CCTV footage is a rare-event problem where training on labeled accident video is often prohibited, yet accurate joint localization in time, space, and collision type is required. We present a no-fine-tuning pipeline that elicits this joint output from frozen vision-language models through two ideas. First, a coarse-to-fine two-pass decomposition: a full-video pass at 1 fps produces a coarse (t, x, y, c) tuple, then a second pass at 5 fps within a +/- 3 s window refines time and location, with two deterministic confidence gates that revert to the coarse estimate on boundary hedges or edge-clamped coordinates. Second, a specialist role assignment: Qwen3-VL-Plus handles grounding, Gemini 3.1 Flash-Lite handles typing on a centered video clip. On the ACCIDENT@CVPR 2026 benchmark (2,027 real CCTV videos) we reach ACC^S = 0.539 (95% CI [0.525, 0.553]): +0.127 over the benchmark paper's best-of-baselines oracle (0.412), +0.143 over the strongest single-VLM baseline (Molmo-7B, 0.396), and +0.250 over the naive baseline (0.289). The VLM path uses up to three API calls per video (17% fall back to physics on API failures); the full run costs ~$20.

Jiantang Huang

Temporal Video Grounding Large Vision-Language Models Anomaly Localization Vision-Language Grounding

May 1, 2026

Static and Dynamic Graph Alignment Network for Temporal Video Grounding

Temporal Video Grounding (TVG) aims to localize temporal moments in an untrimmed video that semantically correspond to given natural language queries. Recently, Graph Convolutional Networks (GCN) have been widely adopted in TVG to model temporal relations among video clips and enhance contextual reasoning by constructing clip-level graphs. Despite their effectiveness, existing GCN-based TVG methods encounter three critical bottlenecks: 1) Most methods construct graph nodes using either static or dynamic features alone, resulting in incomplete visual representation and overlooking complementary semantics, 2) Most methods construct temporal graphs in a query-agnostic manner, leading to inefficient feature interaction within the temporal graph representation, and 3) Most methods often suffer from a single-granularity semantic matching, while direct training on complex temporal localization task may lead to slow convergence and suboptimal precision. To address these challenges, we propose Static and Dynamic Graph Alignment Network (SDGAN). First, SDGAN jointly exploits static and dynamic visual features to construct two complementary temporal graphs and performs Position-wise Nodes Alignment, enabling more expressive and robust visual representation. Second, SDGAN introduces Query-Clip Contrastive Learning and Adaptive Graph Modeling to explicitly align visual clips with their corresponding textual queries, yielding query-aware visual representations. Third, SDGAN incorporates multi-granularity temporal proposals within Progressive Easy-to-Hard Training Strategy, effectively bridging coarse-grained semantic localization and fine-grained temporal boundary refinement. Extensive experiments on three benchmark datasets demonstrate that SDGAN achieves superior performance across complex TVG scenarios. Codes and datasets are available at https://github.com/ZhanJieHu/SDGAN.

Zhanjie Hu, Bolin Zhang, Jianhua Wang +5

Faculty of Electronic Engineering and Computer Science, Ningbo University, Ningbo, China · College of Computer Science, Inner Mongolia University, Hohhot, China · College of Computing and Engineering, Hunan Normal University, Changsha, China +4

Temporal Video Grounding Temporal GNNs Vision-Language Alignment

Apr 30, 2026

ClipTBP: Clip-Pair based Temporal Boundary Prediction with Boundary-Aware Learning for Moment Retrieval

Video moment retrieval is the task of retrieving specific segments of a video corresponding to a given text query. Recent studies have been conducted to improve multimodal alignment performance through visual-linguistic similarity learning at the snippet-level and transformer-based temporal boundary regression. However, existing models do not calculate similarity by considering the relationships between multiple answer segments that match the query. Therefore, existing models are easily influenced by visually similar segments in the surrounding context. Existing models calculate similarity at the snippet-level and ignore the relationships between multiple answer segments corresponding to a single query. Therefore, they struggle to exclude segments irrelevant to the query. To address this issues, we propose ClipTBP, a clip-pair temporal boundary prediction framework based on boundary-aware learning. ClipTBP introduces a clip-level alignment loss for explicitly learning the semantic relationship between answer segments. ClipTBP also predicts accurate temporal boundaries by applying both main boundary loss and auxiliary boundary loss. ClipTBP consistently improves performance when applied to various existing models and demonstrates more robust boundary prediction performance even in ambiguous query scenarios.

Ji-Hyeon Kim, Ho-Joong Kim, Seong-Whan Lee

Dept. of Artificial Intelligence, Korea University, Seoul 02841, Republic of Korea

Temporal Video Grounding Cross-Modal Alignment

Apr 28, 2026

OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding

Video Temporal Grounding (VTG), the task of localizing video segments from text queries, struggles in open-world settings due to limited dataset scale and semantic diversity, causing performance gaps between common and rare concepts. To overcome these limitations, we introduce OmniVTG, a new large-scale dataset for open-world VTG, coupled with a Self-Correction Chain-of-Thought (CoT) training paradigm designed to enhance the grounding capabilities of Multimodal Large Language Models (MLLMs). Our OmniVTG is constructed via a novel Semantic Coverage Iterative Expansion pipeline, which first identifies gaps in the vocabulary of existing datasets and collects videos that are highly likely to contain these target concepts. For high-quality annotation, we leverage the insight that modern MLLMs excel at dense captioning more than direct grounding and design a caption-centric data engine to prompt MLLMs to generate dense, timestamped descriptions. Beyond the dataset, we observe that simple supervised finetuning (SFT) is insufficient, as a performance gap between rare and common concepts still persists. We find that MLLMs' video understanding ability significantly surpasses their direct grounding ability. Based on this, we propose a Self-Correction Chain-of-Thought (CoT) training paradigm. We train the MLLM to first predict, then use its understanding capabilities to reflect on and refine its own predictions. This capability is instilled via a three-stage pipeline of SFT, CoT finetuning, and reinforcement learning. Extensive experiments show our approach not only excels at open-world grounding in our OmniVTG dataset but also achieves state-of-the-art zero-shot performance on four existing VTG benchmarks. Code is available at https://github.com/oceanflowlab/OmniVTG.

Minghang Zheng, Zihao Yin, Yi Yang +2

Wangxuan Institute of Computer Technology, Peking University · Central Media Technology Institute, Huawei Technologies Ltd. · State Key Laboratory of General Artificial Intelligence, Peking University +1

Temporal Video Grounding LLM Self-Correction LLM Grounding

Apr 28, 2026

FCMBench-Video: Benchmarking Document Video Intelligence

Document understanding is a critical capability in financial credit review, onboarding, and remote verification, where both decision accuracy and evidence traceability matter. Compared with static document images, document videos present a temporally redundant and sequentially unfolding evidence stream, require evidence integration across frames, and preserve acquisition-process cues relevant to authenticity-sensitive and anti-fraud review. We introduce FCMBench-Video, a benchmark for document-video intelligence that evaluates document perception, temporal grounding, and evidence-grounded reasoning under realistic capture conditions. For privacy-compliant yet realistic data at scale, we organize construction as an atomic-acquisition and composition workflow that records reusable single-document clips, applies controlled degradations, and assembles long-form multi-document videos with prescribed temporal spans. FCMBench-Video is built from 495 atomic videos composed into 1,200 long-form videos paired with 11,322 expert-annotated question--answer instances, covering 28 document types over 20s--60s duration tiers and 5,960 Chinese / 5,362 English instances. Evaluations on nine recent Video-MLLMs show that FCMBench-Video provides meaningful separation across systems and capabilities: counting is the most duration-sensitive task, Cross-Document Validation and Evidence-Grounded Selection probe higher-level evidence integration, and Visual Prompt Injection provides a complementary robustness dimension. The overall score distribution is broad and approximately bell-shaped, indicating a benchmark that is neither saturated nor dominated by trivial cases. Together, these results position FCMBench-Video as a reproducible benchmark for tracking Video-MLLM progress on document-video understanding and probing capability boundaries in authenticity-sensitive credit-domain applications.

Runze Cui, Fangxin Shang, Yehui Yang +3

AI Lab, Qifu Technology, Beijing, China · School of Future Technology, South China University of Technology, Guangzhou, China · Pazhou Lab, Guangzhou, China +1

VLM Evaluation Document Understanding Temporal Video Grounding Video Understanding VLM Robustness Evidence-Grounded Reasoning

Apr 25, 2026

StoryTR: Narrative-Centric Video Temporal Retrieval with Theory of Mind Reasoning

Current video moment retrieval excels at action-centric tasks but struggles with narrative content. Models can see what is happening but fail to reason why it matters. This semantic gap stems from the lack of Theory of Mind (ToM): the cognitive ability to infer implicit intentions, mental states, and narrative causality from surface-level observations. We introduce StoryTR, the first video moment retrieval benchmark requiring ToM reasoning, comprising 8.1k samples from narrative short-form videos (shorts/reels). These videos present an ideal testbed. Their high information density encodes meaning through subtle multimodal cues. For instance, a glance paired with a sigh carries entirely different semantics than the glance alone. Yet multimodal perception alone is insufficient; ToM is required to decode that a character smiling'' may actually be concealing hostility.'' To teach models this reasoning capability, we propose an Agentic Data Pipeline that generates training data with explicit three-tier ToM chains (intent decoding, narrative reasoning, boundary localization). Experiments reveal the severity of the reasoning gap: Gemini-3.0-Pro achieves only 0.53 Avg IoU on StoryTR. However, our 7B Shorts-Moment model, trained on ToM-guided data, improves +15.1% relative IoU over baselines, demonstrating that narrative reasoning capability matters more than parameter scale.

Xuanyue Zhong, Yuqiang Xie, Guanqun Bi +2

Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong · SkyReels, Skywork AI · Independent Researcher

Temporal Video Grounding Video Understanding Theory of Mind Multimodal Reasoning Video Moment Retrieval Video Retrieval+1

Apr 24, 2026

Towards Temporal Compositional Reasoning in Long-Form Sports Videos

Sports videos are a challenging domain for multimodal understanding because they involve complex and dynamic human activities. Despite rapid progress in Multimodal Large Language Models (MLLMs), long-horizon reasoning in sports videos remains difficult, as answering questions requires both locating temporally sparse evidence and integrating it into reasoning. We attribute this limitation to two closely coupled factors: insufficient supervision over temporally dispersed evidence, and the lack of methods that require models to identify, localize, and justify temporal evidence. To address these gaps, we introduce SportsTime, a large-scale benchmark for long-form sports video understanding, comprising 14K+ open-ended QA pairs and 50K+ step-wise temporal evidence annotations. Building on SportsTime, we propose Chain-of-Time Reasoning (CoTR), which treats reasoning as a process of temporally grounded evidence composition. Specifically, during training, CoTR introduces a temporal-reward GRPO to encourage temporally grounded reasoning. During inference, it employs an anchor-observe-infer evidence-seeking loop to iteratively localize, verify, and compose temporal evidence before producing the final answer. Experiments demonstrate the usefulness of SportsTime as a benchmark and the effectiveness of CoTR, which consistently improves temporal compositional reasoning and step-wise grounding quality over strong MLLM baselines.

Siyu Cao, Lu Zhang, Ruizhe Zeng +1

MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China · Nanjing Artificial Intelligence Research of IA, Nanjing, 211100, China

Temporal Video Grounding Temporal Reasoning Sports Video Analysis Multimodal QA Long-Video Understanding

Apr 23, 2026

Grounding Video Reasoning in Physical Signals

Physical video understanding requires more than naming an event correctly. A model can answer a question about pouring, sliding, or collision from textual regularities while still failing to localize the event in time or space. We introduce a grounded benchmark for physical video understanding that extends the what--when--where evaluation structure of V-STaR to four video sources, six physics domains, three prompt families (physics, vstar_like, and neutral_rstr), and four input conditions (original, shuffled, ablated, and frame-masked). The benchmark contains 1,560 base video clips from SSV2, YouCook2, HoloAssist, and Roundabout-TAU. Each clip is first converted into a shared grounded event record, and the three query families are derived from that record. Temporal and spatial targets are shared across prompt families, while the non-physics families use deterministic family-appropriate semantic a_what targets derived from the same record. Across models and prompt families, physics remains the strongest regime overall, vstar_like is the clearest non-physics semantic comparison, and neutral_rstr behaves as a harder templated control. Prompt-family robustness is selective rather than universal, perturbation gains cluster in weak original cases, and spatial grounding is the weakest across settings. These results suggest that video Q&A reasoning benchmarks shall report physically grounded, prompt-aware, and perturbation-aware diagnostics alongside aggregate accuracy.

Alibay Osmanli, Zixu Cheng, Shaogang Gong

Queen Mary University of London

Temporal Video Grounding Video QA Visually Grounded Reasoning Visual Grounding Physical Reasoning in Video

Apr 14, 2026

Unlocking the Potential of Grounding DINO in Videos: Parameter-Efficient Adaptation for Limited-Data Spatial-Temporal Localization

Spatio-temporal video grounding (STVG) aims to localize queried objects within dynamic video segments. Prevailing fully-trained approaches are notoriously data-hungry. However, gathering large-scale STVG data is exceptionally challenging: dense frame-level bounding boxes and complex temporal language alignments are prohibitively expensive to annotate, especially for specialized video domains. Consequently, conventional models suffer from severe overfitting on these inherently limited datasets, while zero-shot foundational models lack the task-specific temporal awareness needed for precise localization. To resolve this small-data challenge, we introduce ST-GD, a data-efficient framework that adapts pre-trained 2D visual-language models (e.g., Grounding DINO) to video tasks. To avoid destroying pre-trained priors on small datasets, ST-GD keeps the base model frozen and strategically injects lightweight adapters (~10M trainable parameters) to instill spatio-temporal awareness, alongside a novel temporal decoder for boundary prediction. This design naturally counters data scarcity. Consequently, ST-GD excels in data-scarce scenarios, achieving highly competitive performance on the limited-scale HC-STVG v1/v2 benchmarks, while maintaining robust generalization on the VidSTG dataset. This validates ST-GD as a powerful paradigm for complex video understanding under strict small-data constraints.

Zanyi Wang, Fan Li, Dengyang Jiang +4

SGIT AI Lab, State Grid Corporation of China · University of HongKong · Zhejiang University of Technology

Temporal Video Grounding VLM Adaptation Parameter-Efficient Fine-Tuning

Apr 13, 2026

ViLL-E: Video LLM Embeddings for Retrieval

Video Large Language Models (VideoLLMs) excel at video understanding tasks where outputs are textual, such as Video Question Answering and Video Captioning. However, they underperform specialized embedding-based models in Retrieval tasks, such as Text-toVideo Retrieval and Moment Retrieval. We introduce ViLL-E (Video-LLM-Embed), a unified VideoLLM architecture endowed with a novel embedding generation mechanism that allows the model to "think longer" for complex videos and stop early for easy ones. We train this model with a three-stage training methodology combining generative and contrastive learning: initial large-scale pre-training with video-caption pairs; followed by continual training on a smaller, detailed-caption dataset; and concluding with task-specific fine-tuning on a novel multi-task dataset covering Video QA, Temporal Localization, Video Retrieval, and Video-Text Matching. Our model significantly improves temporal localization (on avg. 7% over other VideoLLMs) and video retrieval (up to 4% over dual encoder models), achieving performance comparable to state-of-the-art specialized embedding models while remaining competitive on VideoQA tasks. Furthermore, our joint contrastive-generative training unlocks new zero-shot capabilities, significantly outperforming state-of-the-art methods in composed video retrieval (+5% over SotA) and retrieval from long text (+2% over SotA).

Rohit Gupta, Jayakrishnan Unnikrishnan, Fan Fei +3

Video-Language Models Vision-Language Models Video Retrieval Temporal Video Grounding Composed Video Retrieval

Apr 11, 2026

LVSum: A Benchmark for Timestamp-Aware Long Video Summarization

Long video summarization presents significant challenges for multimodal large language models (MLLMs), particularly in maintaining temporal fidelity over extended durations and producing summaries that are both semantically and temporally grounded. We introduce LVSum, a human-annotated benchmark for evaluating long-form video summarization with fine-grained temporal alignment. LVSum comprises 72 diverse videos spanning 13 domains with an average duration of 16 minutes, each annotated with up to 10 human-generated summaries containing temporal references. We conduct a comprehensive evaluation of leading proprietary and open-source MLLMs using newly introduced LLM-based metrics for content relevance and modality coherence, alongside standard automatic metrics. Our experiments reveal three key findings: (1) transcripts contribute substantially more to summarization quality than visual frames alone, (2) a significant performance gap persists between model-generated and human-written summaries, and (3) current MLLMs exhibit systematic weaknesses in temporal grounding, instruction adherence, and cross-modal coherence. We release the dataset and code.

Alkesh Patel, Melis Ozyildirim, Ying-Chang Cheng +1

Apple

Video Summarization Video-Language Model Evaluation Multimodal Large Language Models Temporal Video Grounding

Apr 10, 2026

How Should Video LLMs Output Time? An Analysis of Efficient Temporal Grounding Paradigms

While Multimodal Large Language Models (MLLMs) have advanced Video Temporal Grounding (VTG), existing methods often couple output paradigms with different backbones, datasets, and training protocols. This makes it challenging to isolate the specific impact of the output design. Additionally, as VTG systems are increasingly considered for resource-constrained edge deployment, the trade-off between output formulation and system-level efficiency requires systematic investigation. In this paper, we present a controlled empirical study comparing three dominant VTG output paradigms: Text Numeral Generation, Temporal Token Generation, and Continuous Temporal Decoding. We evaluate these paradigms across identical compact VLMs (SmolVLM2, FastVLM, and Molmo2) using consistent datasets and LoRA fine-tuning protocols. Evaluations on Charades-STA, QVHighlights, and YouCook2 measure both localization accuracy and system efficiency, including inference latency, training throughput, and parameter overhead. Our results demonstrate that the choice of output formulation significantly affects both grounding accuracy and computational cost, independent of model scale. Specifically, the continuous distribution paradigm consistently achieves the most favorable efficiency-accuracy trade-off on the Pareto frontier, delivering robust localization with minimal latency overhead. These findings provide objective empirical guidelines for designing efficient, deployment-ready VTG systems.

Shengji Jin, Yuanhao Zou, Victor Zhu +2

The University of Central Florida · Axon

Temporal Video Grounding Efficient VLM Inference Video-Language Model Evaluation

Apr 9, 2026

UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding

Video temporal grounding (VTG) is typically tackled with dataset-specific models that transfer poorly across domains and query styles. Recent efforts to overcome this limitation have adapted large multimodal language models (MLLMs) to VTG, but their high compute cost and limited video context still hinder long-video grounding. We instead scale unified supervision while keeping the model lightweight. We present UniversalVTG, a single VTG model trained with large-scale cross-dataset pretraining. An offline Query Unifier canonicalizes heterogeneous query formats into a shared declarative space, reducing linguistic mismatch and preventing the negative transfer observed under naïve joint training. Combined with an efficient grounding head, UniversalVTG scales to long, untrimmed videos. Across diverse benchmarks-GoalStep-StepGrounding, Ego4D-NLQ, TACoS, Charades-STA, and ActivityNet-Captions-one UniversalVTG checkpoint achieves state-of-the-art performance versus dedicated VTG models. Moreover, despite being

>100\times

smaller than recent MLLM-based approaches, UniversalVTG matches or exceeds their accuracy on multiple benchmarks, offering a practical alternative to parameter-heavy MLLMs.

Joungbin An, Agrim Jain, Kristen Grauman

The University of Texas at Austin

Temporal Video Grounding

Apr 9, 2026

Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding

Spatio-Temporal Video Grounding requires jointly localizing target objects across both temporal and spatial dimensions based on natural language queries, posing fundamental challenges for existing Multimodal Large Language Models (MLLMs). We identify two core challenges: entangled spatio-temporal alignment, arising from coupling two heterogeneous sub-tasks within the same autoregressive output space, and dual-domain visual token redundancy, where target objects exhibit simultaneous temporal and spatial sparsity, rendering the overwhelming majority of visual tokens irrelevant to the grounding query. To address these, we propose Bridge-STG, an end-to-end framework that decouples temporal and spatial localization while maintaining semantic coherence. While decoupling is the natural solution to this entanglement, it risks creating a semantic gap between the temporal MLLM and the spatial decoder. Bridge-STG resolves this through two pivotal designs: the Spatio-Temporal Semantic Bridging (STSB) mechanism with Explicit Temporal Alignment (ETA) distills the MLLM's temporal reasoning context into enriched bridging queries as a robust semantic interface; and the Query-Guided Spatial Localization (QGSL) module leverages these queries to drive a purpose-built spatial decoder with multi-layer interactive queries and positive/negative frame sampling, jointly eliminating dual-domain visual token redundancy. Extensive experiments across multiple benchmarks demonstrate that Bridge-STG achieves state-of-the-art performance among MLLM-based methods. Bridge-STG improves average m_vIoU from

26.4

to

34.3

on VidSTG and demonstrates strong cross-task transfer across various fine-grained video understanding tasks under a unified multi-task training regime.

Xuezhen Tu, Jingyu Wu, Fangyu Kang +4

Shanghai Jiao Tong University China · ZTE Corporation China

Vision-Language Grounding Temporal Video Grounding Unified Multimodal Models

Apr 9, 2026

Open-Ended Video Game Glitch Detection with Agentic Reasoning and Temporal Grounding

Open-ended video game glitch detection aims to identify glitches in gameplay videos, describe them in natural language, and localize when they occur. Unlike conventional game glitch understanding tasks which have largely been framed as image-level recognition or closed-form question answering, this task requires reasoning about game-specific dynamics such as mechanics, physics, rendering, animation, and expected state transitions directly over continuous gameplay videos and distinguishing true glitches from unusual but valid in-game events. To support this task, we introduce VideoGlitchBench, the first benchmark for open-ended video game glitch detection with temporal localization. VideoGlitchBench contains 5,238 gameplay videos from 120 games, each annotated with detailed glitch descriptions and precise temporal spans, enabling unified evaluation of semantic understanding and temporal grounding. We further propose GliDe, an agentic framework with three key components: a game-aware contextual memory for informed reasoning, a debate-based reflector for multi-perspective glitch detection and verification, and an event-level grounding module that recovers complete glitch intervals from fragmented temporal evidence. We also design a task-specific evaluation protocol that jointly measures semantic fidelity and temporal accuracy. Experiments show that this task remains highly challenging for current multimodal models, while GliDe achieves substantially stronger performance than corresponding vanilla model baselines.

Muyang Zheng, Tong Zhou, Geyang Wu +3

University of California, Davis Davis, California, USA · Virginia Polytechnic Institute and State University Blacksburg, Virginia, USA

Video Anomaly Detection Temporal Video Grounding

Apr 8, 2026

Spatio-Temporal Grounding of Large Language Models from Perception Streams

Embodied-AI agents must reason about how objects move and interact in 3-D space over time, yet existing smaller frontier Large Language Models (LLMs) still mis-handle fine-grained spatial relations, metric distances, and temporal orderings. We introduce the general framework Formally Explainable Spatio-Temporal Scenes (FESTS) that injects verifiable spatio-temporal supervision into an LLM by compiling natural-language queries into Spatial Regular Expression (SpRE) -- a language combining regular expression syntax with S4u spatial logic and extended here with universal and existential quantification. The pipeline matches each SpRE against any structured video log and exports aligned (query, frames, match, explanation) tuples, enabling unlimited training data without manual labels. Training a 3-billion-parameter model on 27k such tuples boosts frame-level F1 from 48.5% to 87.5%, matching GPT-4.1 on complex spatio-temporal reasoning while remaining two orders of magnitude smaller, and, hence, enabling spatio-temporal intelligence for Video LLM.

Jacob Anderson, Bardh Hoxha, Georgios Fainekos +2

Toyota Motor North America Research & Development, Ann Arbor, MI, USA

Spatiotemporal Reasoning LLM Grounding Temporal Video Grounding

Apr 3, 2026

A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos

Temporal sentence grounding in videos (TSGV) aims to localize a temporal segment that semantically corresponds to a sentence query from an untrimmed video. Most current methods adopt pre-trained query-agnostic visual encoders for offline feature extraction, and the video backbones are frozen and not optimized for TSGV. This leads to a task discrepancy issue for the video backbone trained for visual classification, but utilized for TSGV. To bridge this gap, we propose a fully end-to-end paradigm that jointly optimizes the video backbone and localization head. We first conduct an empirical study validating the effectiveness of end-to-end learning over frozen baselines across different model scales. Furthermore, we introduce a Sentence Conditioned Adapter (SCADA), which leverages sentence features to train a small portion of video backbone parameters adaptively. SCADA facilitates the deployment of deeper network backbones with reduced memory and significantly enhances visual representation by modulating feature maps through precise integration of linguistic embeddings. Experiments on two benchmarks show that our method outperforms state-of-the-art approaches. The code and models will be released.

Allen He, Qi Liu, Kun Liu +2

BASIS International School Park Lane Harbour · UCAS · JD Explore Academy +1

Temporal Video Grounding Parameter-Efficient Fine-Tuning

Apr 2, 2026

GroundVTS: Visual Token Sampling in Multimodal Large Language Models for Video Temporal Grounding

Video temporal grounding (VTG) is a critical task in video understanding and a key capability for extending video large language models (Vid-LLMs) to broader applications. However, existing Vid-LLMs rely on uniform frame sampling to extract video information, resulting in a sparse distribution of key frames and the loss of crucial temporal cues. To address this limitation, we propose Grounded Visual Token Sampling (GroundVTS), a Vid-LLM architecture that focuses on the most informative temporal segments. GroundVTS employs a fine-grained, query-guided mechanism to filter visual tokens before feeding them into the LLM, thereby preserving essential spatio-temporal information and maintaining temporal coherence. Futhermore, we introduce a progressive optimization strategy that enables the LLM to effectively adapt to the non-uniform distribution of visual features, enhancing its ability to model temporal dependencies and achieve precise video localization. We comprehensively evaluate GroundVTS on three standard VTG benchmarks, where it outperforms existing methods, achieving a 7.7-point improvement in mIoU for moment retrieval and 12.0-point improvement in mAP for highlight detection. Code is available at https://github.com/Florence365/GroundVTS.

Rong Fan, Kaiyan Xiao, Minghao Zhu +3

Newcapec AI Research · Fudan University · Tongji University

Temporal Video Grounding Video-Language Models Query-Aware Video Frame Selection Visual Token Pruning

Apr 2, 2026

VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification

Video multimodal large language models achieve strong results on existing benchmarks, but answer accuracy alone does not establish whether they can locate the evidence needed to answer a question. We introduce VideoZeroBench, a challenging long-video benchmark with manually annotated question-answer pairs spanning 13 video domains. Questions target fine-grained cues, fleeting events, and evidence distributed across multiple segments. Temporal intervals and key-frame boxes are annotated where applicable. All questions undergo two rounds of cross-verification for answer validity and evidence quality. Our five-level diagnostic protocol compares answering with and without evidence hints, then combines answer correctness with independently evaluated temporal and spatial grounding. Across 19 evaluated models, the best standard QA accuracy is 24.8% (Level-3), achieved by Gemini-3.7-Flash. No model exceeds 1.8% when correct answers and accurate spatio-temporal localization are jointly required (Level-5). Analyses of atomic abilities, evidence spans, input modalities, and thinking-with-videos inference further characterize where the evaluated systems struggle. These findings motivate more precise evidence search and localization for long-video question answering. Our code and data are publicly released.

Jiahao Meng, Yue Tan, Qi Xu +9

PKU · WHU · CASIA +2

Video-Language Model Evaluation Long-Video QA Temporal Video Grounding

Apr 1, 2026

GRAZE: Grounded Refinement and Motion-Aware Zero-Shot Event Localization

American football practice generates video at scale, yet the interaction of interest occupies only a brief window of each long, untrimmed clip. Reliable biomechanical analysis, therefore, depends on spatiotemporal localization that identifies both the interacting entities and the onset of contact. We study First Point of Contact (FPOC), defined as the first frame in which a player physically touches a tackle dummy, in unconstrained practice footage with camera motion, clutter, multiple similarly equipped athletes, and rapid pose changes around impact. We present GRAZE, a training-free pipeline for FPOC localization that requires no labeled tackle-contact examples. GRAZE uses Grounding DINO to discover candidate player-dummy interactions, refines them with motion-aware temporal reasoning, and uses SAM2 as an explicit pixel-level verifier of contact rather than relying on detection confidence alone. This separation between candidate discovery and contact confirmation makes the approach robust to cluttered scenes and unstable grounding near impact. On 738 tackle-practice videos, GRAZE produces valid outputs for 97.4% of clips and localizes FPOC within

\pm

10 frames on 77.5% of all clips and within

\pm

20 frames on 82.7% of all clips. These results show that frame-accurate contact onset localization in real-world practice footage is feasible without task-specific training.

Syed Ahsan Masud Zaidi, Lior Shamir, William Hsu +2

Kansas State University, Manhattan, KS, USA · Albright College, Reading, PA, USA

Sports Video Analysis Temporal Action Localization Temporal Video Grounding

Mar 28, 2026

Incentivizing Temporal-Awareness in Egocentric Video Understanding Models

Multimodal large language models (MLLMs) have recently shown strong performance in visual understanding, yet they often lack temporal awareness, particularly in egocentric settings where reasoning depends on the correct ordering and evolution of events. This deficiency stems in part from training objectives that fail to explicitly reward temporal reasoning and instead rely on frame-level spatial shortcuts. To address this limitation, we propose Temporal Global Policy Optimization (TGPO), a reinforcement learning with verifiable rewards (RLVR) algorithm designed to incentivize temporal awareness in MLLMs. TGPO contrasts model outputs generated from temporally ordered versus shuffled video frames to derive calibrated, globally normalized reward signals that explicitly favor temporally coherent reasoning. Integrated with GRPO and GSPO, TGPO supports cold-start RL training and effectively suppresses spatial shortcut behaviors learned by existing MLLMs. Experiments across five egocentric video benchmarks demonstrate that TGPO consistently improves temporal grounding and causal coherence, outperforming prior RL-based video reasoning approaches. Our results suggest that TGPO offers a simple and scalable pathway toward temporally robust MLLMs for egocentric video understanding.

Zhiyang Xu, Tian Qin, Bowen Jin +4

Virginia Tech · Harvard University · UIUC +2

Egocentric Video Understanding RL for VLMs Temporal Video Grounding Reinforcement Learning with Verifiable Rewards

Mar 26, 2026

SlotVTG: Object-Centric Adapter for Generalizable Video Temporal Grounding

Multimodal Large Language Models (MLLMs) have shown strong performance on Video Temporal Grounding (VTG). However, their coarse recognition capabilities are insufficient for fine-grained temporal understanding, making task-specific fine-tuning indispensable. This fine-tuning causes models to memorize dataset-specific shortcuts rather than faithfully grounding in the actual visual content, leading to poor Out-of-Domain (OOD) generalization. Object-centric learning offers a promising remedy by decomposing scenes into entity-level representations, but existing approaches require re-running the entire multi-stage training pipeline from scratch. We propose SlotVTG, a framework that steers MLLMs toward object-centric, input-grounded visual reasoning at minimal cost. SlotVTG introduces a lightweight slot adapter that decomposes visual tokens into abstract slots via slot attention and reconstructs the original sequence, where objectness priors from a self-supervised vision model encourage semantically coherent slot formation. Cross-domain evaluation on standard VTG benchmarks demonstrates that our approach significantly improves OOD robustness while maintaining competitive In-Domain (ID) performance with minimal overhead.

Jiwook Han, Geo Ahn, Youngrae Kim +1

Kyung Hee University · University of Southern California

Temporal Video Grounding VLM Adaptation OOD Generalization Object-Centric Representation Learning

Mar 26, 2026

CVA: Context-aware Video-text Alignment for Video Temporal Grounding

We propose Context-aware Video-text Alignment (CVA), a novel framework to address a significant challenge in video temporal grounding: achieving temporally sensitive video-text alignment that remains robust to irrelevant background context. Our framework is built on three key components. First, we propose Query-aware Context Diversification (QCD), a new data augmentation strategy that ensures only semantically unrelated content is mixed in. It builds a video-text similarity-based pool of replacement clips to simulate diverse contexts while preventing the ``false negative" caused by query-agnostic mixing. Second, we introduce the Context-invariant Boundary Discrimination (CBD) loss, a contrastive loss that enforces semantic consistency at challenging temporal boundaries, making their representations robust to contextual shifts and hard negatives. Third, we introduce the Context-enhanced Transformer Encoder (CTE), a hierarchical architecture that combines windowed self-attention and bidirectional cross-attention with learnable queries to capture multi-scale temporal context. Through the synergy of these data-centric and architectural enhancements, CVA achieves state-of-the-art performance on major VTG benchmarks, including QVHighlights and Charades-STA. Notably, our method achieves a significant improvement of approximately 5 points in Recall@1 (R1) scores over state-of-the-art methods, highlighting its effectiveness in mitigating false negatives.

Sungho Moon, Seunghun Lee, Jiwan Seo +1

Daegu Gyeongbuk Institute of Science and Technology (DGIST), Republic of Korea

Temporal Video Grounding Vision-Language Alignment

Mar 25, 2026

Knowledge-Refined Dual Context-Aware Network for Partially Relevant Video Retrieval

Retrieving partially relevant segments from untrimmed videos remains difficult due to two persistent challenges: the mismatch in information density between text and video segments, and limited attention mechanisms that overlook semantic focus and event correlations. We present KDC-Net, a Knowledge-Refined Dual Context-Aware Network that tackles these issues from both textual and visual perspectives. On the text side, a Hierarchical Semantic Aggregation module captures and adaptively fuses multi-scale phrase cues to enrich query semantics. On the video side, a Dynamic Temporal Attention mechanism employs relative positional encoding and adaptive temporal windows to highlight key events with local temporal coherence. Additionally, a dynamic CLIP-based distillation strategy, enhanced with temporal-continuity-aware refinement, ensures segment-aware and objective-aligned knowledge transfer. Experiments on PRVR benchmarks show that KDC-Net consistently outperforms state-of-the-art methods, especially under low moment-to-video ratios.

Junkai Yang, Qirui Wang, Yaoqing Jin +3

School of Software Engineering, Xi’an Jiaotong University · Faculty of Computer Science, Electrical Engineering and Information Technology, Universität Stuttgart

Information Retrieval Temporal Video Grounding

Mar 24, 2026

ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance

Despite decades of work, surveillance still struggles in searching and reasoning about specific targets across long, multi-camera videos. Existing methods - tracking, retrieval, and video LLMs require heavy manual filtering, capture only shallow attributes, and fail at temporal understanding. Prior benchmarks are also limited to basic retrieval and question answering, without addressing real world challenges that often involve multimodal queries and temporal grounding (e.g., "When did this person join the fight?" with the person's image). To address this gap, we introduce ForeSeaQA, a new benchmark specifically designed for video QA with image-and-text queries and timestamped annotations of key events. The dataset consists of long-horizon surveillance footage paired with diverse multimodal questions, enabling systematic evaluation of retrieval, temporal grounding, and multimodal reasoning in realistic forensic conditions. Not limited to this benchmark, we propose ForeSea, an AI forensic search system with a 3-stage, plug-and-play pipeline. (1) A tracking module filters irrelevant footage; (2) a multimodal embedding module indexes the remaining clips; and (3) during inference, the system retrieves top-K candidate clips for a video LLM to answer queries and localize events. On ForeSeaQA benchmark, ForeSea improves accuracy by 3.1 points and temporal IoU by 10.1 points over prior retrieval-augmented baselines. To our knowledge, ForeSeaQA is the first benchmark to support complex multimodal queries with precise temporal grounding, and ForeSea is the first VideoRAG system built to excel in this setting.

Hyojin Park, Yi Li, Janghoon Cho +8

Qualcomm AI Research, San Diego, CA, USA · Kyunghee University, Gyeonggi, South Korea

Video Surveillance Multimodal IR Temporal Video Grounding Digital Forensics Video QA Multimodal RAG+3

Mar 23, 2026

GenSpan: Generation-Calibrated Motion Span Priors for Multi-Verb Video Corpus Moment Retrieval

Video Corpus Moment Retrieval (VCMR) aims to retrieve both the correct video and its temporal segment corresponding to a natural-language query, a task that is especially challenging for multi-verb queries where temporal action ordering is critical. Existing approaches often rely solely on text or static images and struggle to capture implicit motion dynamics, leading to retrieval errors and temporal misalignment. We propose GenSpan, a generation-calibrated VCMR framework that constructs short auxiliary videos from LLM-selected subtitle cues and decomposed sub-events, using these as temporal priors rather than direct retrieval targets. A token selector filters candidate-video features aligned with generated motion, and a bidirectional state-space model efficiently predicts video-moment tuples. Experiments on TVR and ActivityNet-Captions demonstrate that GenSpan improves corpus-level retrieval and moment localization, particularly for complex multi-action queries, while reducing computational cost compared to state-of-the-art multimodal baselines.

Yunzhuo Sun, Xinyue Liu, Yanyang Li +4

Dalian University of Technology

Video Moment Retrieval Video Retrieval Temporal IR Vision-Language Retrieval Temporal Video Grounding

Mar 19, 2026

Learning Consistent Temporal Grounding between Related Tasks in Sports Coaching

Video-LLMs often attend to irrelevant frames, which is especially detrimental for sports coaching tasks requiring precise temporal grounding. Yet obtaining frame-level supervision is challenging: expensive to collect from humans and unreliable from other models. We improve temporal grounding without additional annotations by exploiting the observation that related tasks, such as generation and verification, must attend to the same frames. We enforce this via a self-consistency objective over select visual attention maps of tightly-related tasks. Using VidDiffBench, which provides ground-truth keyframe annotations, we first validate that attention misallocation is a significant bottleneck. We then show that training with our objective yields gains of +3.0%, +14.1% accuracy and +0.9 BERTScore over supervised finetuning across three sports coaching tasks: Exact, FitnessQA, and ExpertAF, even surpassing closed-source models.

Arushi Rai, Adriana Kovashka

University of Pittsburgh, Pittsburgh PA 15260, USA

Temporal Video Grounding Temporal Attention Sports Video Analysis Consistency Regularization

Mar 18, 2026

Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos

The transition from image to video understanding requires vision-language models (VLMs) to shift from recognizing static patterns to reasoning over temporal dynamics such as motion trajectories, speed changes, and state transitions. Yet current post-training methods fall short due to two critical limitations: (1) existing datasets often lack temporal-centricity, where answers can be inferred from isolated keyframes rather than requiring holistic temporal integration; and (2) training data generated by proprietary models contains systematic errors in fundamental temporal perception, such as confusing motion directions or misjudging speeds. We introduce SynRL, a post-training framework that teaches models temporal primitives, the fundamental building blocks of temporal understanding including direction, speed, and state tracking. Our key insight is that these abstract primitives, learned from programmatically generated synthetic videos, transfer effectively to real-world scenarios. We decompose temporal understanding into short-term perceptual primitives (speed, direction) and long-term cognitive primitives, constructing 7.7K CoT and 7K RL samples with ground-truth frame-level annotations through code-based video generation. Despite training on simple geometric shapes, SynRL achieves substantial improvements across 15 benchmarks spanning temporal grounding, complex reasoning, and general video understanding. Remarkably, our 7.7K synthetic CoT samples outperform Video-R1 with 165K real-world samples. We attribute this to fundamental temporal skills, such as tracking frame by frame changes and comparing velocity, that transfer effectively from abstract synthetic patterns to complex real-world scenarios. This establishes a new paradigm for video post-training: video temporal learning through carefully designed synthetic data provides a more cost efficient scaling path.

Songtao Jiang, Sibo Song, Chenyi Zhou +12

Zhejiang University · Qwen Team, Alibaba Group · Shanghai Jiao Tong University +1

VLM Post-Training Temporal Video Understanding Vision-Language Models Temporal Video Grounding

Mar 15, 2026

VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting

Video reasoning requires models to locate and track question-relevant evidence across frames. While reinforcement learning (RL) with verifiable rewards improves accuracy, it still struggles to achieve reliable spatio-temporal grounding during the reasoning process. Moreover, improving grounding typically relies on scaled training data or inference-time perception tools, which increases annotation cost or computational cost. To address this challenge, we propose VisonCoach, an input-adaptive RL framework that improves spatio-temporal grounding through visual prompting as training-time guidance. During RL training, visual prompts are selectively applied to challenging inputs to amplify question-relevant evidence and suppress distractors. The model then internalizes these improvements through self-distillation, enabling grounded reasoning directly on raw videos without visual prompting at inference. VisonCoach consists of two components: (1) Visual Prompt Selector, which predicts appropriate prompt types conditioned on the video and question, and (2) Spatio-Temporal Reasoner, optimized with RL under visual prompt guidance and object-aware grounding rewards that enforce object identity consistency and multi-region bounding-box overlap. Extensive experiments demonstrate that VisonCoach achieves state-of-the-art performance under comparable settings, across diverse video reasoning, video understanding, and temporal grounding benchmarks (V-STAR, VideoMME, World-Sense, VideoMMMU, PerceptionTest, and Charades-STA), while maintaining a single efficient inference pathway without external tools. Our results show that visual prompting during training improves grounded video reasoning, while self-distillation enables the model to internalize this ability without requiring prompts at inference time.

Daeun Lee, Shoubin Yu, Yue Zhang +1

University of North Carolina, Chapel Hill, USA

RL for Video Reasoning Video Reasoning Temporal Video Grounding Visual Prompt Learning

Mar 15, 2026

4D Synchronized Fields: Motion-Language Gaussian Splatting for Temporal Scene Understanding

Current 4D representations decouple geometry, motion, and semantics: reconstruction methods discard interpretable motion structure; language-grounded methods attach semantics after motion is learned, blind to how objects move; and motion-aware methods encode dynamics as opaque per-point residuals without object-level organization. We propose 4D Synchronized Fields, a 4D Gaussian representation that learns object-factored motion in-loop during reconstruction and synchronizes language to the resulting kinematics through a per-object conditioned field. Each Gaussian trajectory is decomposed into shared object motion plus an implicit residual, and a kinematic-conditioned ridge map predicts temporal semantic variation, yielding a single representation in which reconstruction, motion, and semantics are structurally coupled and enabling open-vocabulary temporal queries that retrieve both objects and moments. On HyperNeRF, 4D Synchronized Fields achieves 28.52 dB mean PSNR, the highest among all language-grounded and motion-aware baselines, within 1.5 dB of reconstruction-only methods. On targeted temporal-state retrieval, the kinematic-conditioned field attains 0.884 mean accuracy, 0.815 mean vIoU, and 0.733 mean tIoU, surpassing 4D LangSplat (0.620, 0.433, and 0.439 respectively) and LangSplat (0.415, 0.304, and 0.262). Ablation confirms that kinematic conditioning is the primary driver, accounting for +0.45 tIoU over a static-embedding-only baseline. 4D Synchronized Fields is the only method that jointly exposes interpretable motion primitives and temporally grounded language fields from a single trained representation. Code will be released.

Mohamed Rayan Barhdadi, Samir Abdaljalil, Rasul Khanbayov +2

Texas A&M University · Hamad Bin Khalifa University

4D Scene Understanding Dynamic Scene Reconstruction Language-Embedded 3DGS 3D Gaussian Splatting Temporal Video Grounding Object-Centric Representation Learning