Camera Motion Understanding

Follow this topic Ask about this topic

Latest papers

21 papers4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

Fovea-JEPA: Overcoming Geometric Blind Spots in V-JEPA for Camera Motion Recognition
Oct 25, 2026Xiangkun Shi, Hanhui Li, Shiyue Zhang +1Camera Motion Understanding Video Representation Learning
Sun Yat-sen University
MarineLife-16K: An Attribute-Rich Video-Text Dataset for Motion-Aware Marine Video Understanding
Oct 24, 2026Quang-Trung Truong, Thanh-Nghia Nguyen, Phu-Phong Vo +7Video Understanding Multimodal Dataset
Hong Kong University of Science and Technology, Hong Kong SAR · Institute of Advanced Intelligence and Computing (IAIC), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore · University of Information Technology, Vietnam National University, Ho Chi Minh city, Vietnam +3
When Left Is Right? Camera-Motion Understanding beyond Screen
Oct 12, 2026Chong Cheng, Ran Zhang, Xinyuan Li +3Camera Motion Understanding Video-Language Models
The Hong Kong University of Science and Technology (Guangzhou) · Tencent · LIX, Ecole Polytechnique, IP Paris
TSRN-RTVD: Real-Time Video Deblurring System
Oct 6, 2026Nikita Alutis, Danila Evsyukov, Egor Chistov +3Camera Motion Understanding Video Restoration
Lomonosov Moscow State University Moscow, Russian Federation · MSU Institute for Artificial Intelligence Moscow, Russian Federation
Referring Multi-Object Tracking in Moving-Camera Videos via Global Motion Compensation
Oct 3, 2026Hsin-Chen Pai, Jyun-Kai Wang, Yi-Cheng Peng +1Camera Motion Understanding Referring MOT
National Cheng Kung University, Tainan, Taiwan
Unveiling the Value of Motion for Cinematic Camera Trajectories
Sep 30, 2026Ziqi Zhou, Yujian Yuan, Laura Sevilla-LaraCamera-Controlled Video Generation Motion Representation Learning
University of Edinburgh · The Hong Kong University of Science and Technology
Did You Steal My Shot? Pioneering Camera Motion Plagiarism Detection in Generative Videos
Sep 8, 2026Chengguo Zhang, Ping PingCamera Motion Understanding Optical Flow
Hohai University Nanjing, China
What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models
Sep 1, 2026Sharon S. Musa, Fereshteh Forghani, Harrish Thasarathan +3Physical Reasoning in Video Vision Foundation Models
Lassonde School of Engineering, York University, Toronto, Canada · Vector Institute, Toronto, Canada · FAIR, Meta Superintelligence Labs +2
Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation
Aug 11, 2026Dazhao Du, Shiyan Du, Jian Liu +8Temporal Video Grounding Camera Motion Understanding
The Hong Kong University of Science and Technology · Tencent
VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion
Jul 29, 2026Zador Pataki, Paul-Edouard Sarlin, Marc PollefeysMulti-View 3D Reconstruction Camera Pose Estimation
ETH Zurich · Google · Microsoft Spatial AI Lab
Natural Language Camera Movement Understanding
Jul 3, 2026Yuwen Tan, Joey Huang, Jin Huang +2VLM Evaluation Video-Language Models
Boston University, Boston, MA 02215, USA · Pixocial Technology, Bellevue, WA 98004, USA
LIME: Learning Intent-aware Camera Motion from Egocentric Video
Jul 2, 2026Boyang Sun, Jiajie Li, Yung-Hsu Yang +6Active Perception VLMs for Robotics
ETH Zurich · Microsoft · University of Bonn
ParaScale: Scale-Calibrated Camera-Motion Transfer via a Gauge-Invariant Parallax Number
Jun 18, 2026Zijie MengCamera-Controlled Video Generation Camera Motion Understanding
Peking University, China
4DP-QA: Scalable QA for 4D Perception in Vision Language Models
Jun 10, 2026Seokju Cho, Abhishek Badki, Hang Su +5VLM Evaluation VLM Reasoning
1NVIDIA · 2Yale University · *Work done during internship at NVIDIA. +1
A Geometric Framework for Absolute Pose and Velocity Estimation with Event Cameras
Jun 8, 2026Zibin Liu, Shunkun Liang, Banglei Guan +3Camera Motion Understanding Event-Based Vision
College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China · independent researcher, Beijing 100000, China
CamFlow+: Hybrid Motion Bases for 2D Camera Motion Estimation with Stabilization Applications
Jun 4, 2026Haipeng Li, Zhen Liu, Zhanglei Yang +6Optical Flow Camera Pose Estimation
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China · School of Aeronautics and Astronautics, Sichuan University, Chengdu, Sichuan, China · YingCai Honors College, University of Electronic Science and Technology of China, Chengdu, Sichuan, China +2
CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models
May 19, 2026Hsiang-Wei Huang, Junbin Lu, Kuang-Ming Chen +3VLM Evaluation Camera Motion Understanding
Department of Electrical and Computer Engineering, University of Washington, Seattle, USA
MultiLoc: Look Around As You Localize for Fast And Robust Visual Re-localization
Mar 28, 2026Nobel Dang, Bing LiRelative Pose Estimation Camera Pose Estimation
Clemson University, SC, USA
Geometry-Guided Camera Motion Understanding in VideoLLMs
Mar 13, 2026Haoan Feng, Sri Harsha Musunuri, Guan-Ming SuCamera Motion Understanding Video-Language Models
University of Maryland, College Park · Dolby Laboratories Inc.
FLIGHT: Fibonacci Lattice-based Inference for Geometric Heading in real-Time
Feb 26, 2026David Dirnfeld, Fabien Delattre, Pedro Miraldo +1Camera Motion Understanding Camera Pose Estimation
University of Massachusetts Amherst · Mitsubishi Electric Research Laboratories (MERL)
Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video
Dec 13, 2025Daniel Adebi, Sagnik Majumder, Kristen GraumanRelative Pose Estimation Camera Pose Estimation
The University of Texas at Austin, Austin TX 78712, USA

Oct 25, 2026J/K move · Enter open · S save

Fovea-JEPA: Overcoming Geometric Blind Spots in V-JEPA for Camera Motion Recognition

Xiangkun Shi, Hanhui Li, Shiyue Zhang, Xiaodan Liang

Sun Yat-sen University

Camera Motion Understanding Video Representation Learning Joint-Embedding Predictive Architecture

Open paper AskPDF arXiv

Camera motion recognition requires separating viewpoint changes caused by camera translation, rotation, or zoom from object motion and scene dynamics. Video-language models often rely on semantic cues and struggle with the geometric evidence needed for this task. Joint-Embedding Predictive Architectures such as V-JEPA offer strong spatio-temporal representations, but our experiments suggest that they underrepresent geometric cues in some regions. Under temporal-reversal supervision, V-JEPA improves overall but degrades on several motion families, whereas a weaker geometry-oriented VGGT predictor improves across all families. We refer to these geometrically underrepresented regions as geometric blind spots and propose Fovea-JEPA to identify and address them. Using V-JEPA as the base model and VGGT as a geometry expert, we construct intervention pseudo-labels from their prediction errors to weakly supervise a blind-spot predictor. The predictor produces token-wise response maps, which are aggregated into a clip-level intervention score to guide adaptive fusion of visual and geometric features. This selective intervention introduces complementary geometric information while preserving reliable visual predictions. Experiments on CameraMotionDataset, CameraBench, and ShotBench demonstrate the effectiveness of Fovea-JEPA, with gains of 9.67, 8.67, and 24.38 percentage points over previously reported state-of-the-art baselines, respectively. Code and models will be released upon acceptance.