How to Take a Memorable Picture? Empowering Users with Actionable Feedback

Francesco Laiti; Davide Talon; Jacopo Staiano; Elisa Ricci

cs.CVFeb 25, 2026

How to Take a Memorable Picture? Empowering Users with Actionable Feedback

Authors: Francesco Laiti, Davide Talon, Jacopo Staiano, Elisa Ricci

Organizations: University of Trento · University of Pisa · Travelbrain srl · Fondazione Bruno Kessler

Abstract

Image memorability, i.e., how likely an image is to be remembered, has traditionally been studied in computer vision either as a passive prediction task, with models regressing a scalar score, or with generative methods altering the visual input to boost the image likelihood of being remembered. Yet, none of these paradigms supports users at capture time, when the crucial question is how to improve a photo memorability. We introduce the task of Memorability Feedback (MemFeed), where an automated model should provide actionable, human-interpretable guidance to users with the goal to enhance an image future recall. We also present MemCoach, the first approach designed to provide concrete suggestions in natural language for memorability improvement (e.g., "emphasize facial expression," "bring the subject forward"). Our method, based on Multimodal Large Language Models (MLLMs), is training-free and employs a teacher-student steering strategy, aligning the model internal activations toward more memorable patterns learned from a teacher model progressing along least-to-most memorable samples. To enable systematic evaluation on this novel task, we further introduce MemBench, a new benchmark featuring sequence-aligned photoshoots with annotated memorability scores. Our experiments, considering multiple MLLMs, demonstrate the effectiveness of MemCoach, showing consistently improved performance over several zero-shot models. The results indicate that memorability can not only be predicted but also taught and instructed, shifting the focus from mere prediction to actionable feedback for human creators.

Figures & tables

Figure 1: Given an input photo, memorability feedback aims to generate natural-language suggestions to guide users toward a more memorable shot. MemCoach provides memorability-aware feedback, effectively assisting users to capture memorable images.

Figure 2: Overview of MemBench generation and evaluation . Top: Data pipeline for constructing MemBench, including scene grouping, memorability regression, image ranking, and generation of actionable memorability-aware feedback. Bottom: Evaluation pipeline assessing feedback quality through editing-based memorability improvement and perplexity scoring.

Figure 3: MemBench statistics. Data analysis in terms of (a) most frequent words; (b) distribution of memorability scores for the least and most memorable images within each scene; (c) feedback length as measured by content words; and (d) categorization of atomic sub-actions, where the width of each chord indicates the frequency of co-occurrence between categories.

Model	Spearman Rank ( $\uparrow$ )
Inter-annotator ∗	0.68
Qwen2.5VL [ 5 ]	-0.06
InternVL3.5 [ 67 ]	-0.01
Idefics3 [ 39 ]	-0.07
LLaVA-OV [ 3 ]	0.08

Table 1: MLLMs lack memorability understanding. Left: Memorability prediction performance in terms of Spearman’s Rank Correlation

(\uparrow)

(^{*})

is reported from [ 32 ] . Right: Improvement ratio of zero-shot models with respect to the Editing baseline , marginal improvement is observed.

Figure 5: Overview of the proposed method. Ay (a) Contrasting data generation : paired samples are built by coupling the memorability-aware guidance of a teacher MLLM with the neutral responses of a student MLLM on the same scene; Ay (b) Steering vector extraction : activation differences between memorability-aware and neutral feedback are averaged to obtain a memorability steering vector capturing the latent shift toward effective suggestions for memorability; Ay (c) Inference with MLLM steering : the student activations are shifted using the memorability steering vector to produce improved, memorability-oriented feedback without additional training.

Model	Editing		Perplexity ( $\downarrow$ )
Model	IR ( $\uparrow$ )	RM% ( $\uparrow$ )	Perplexity ( $\downarrow$ )
Edit model	0.68	3.72	n.d.
Teacher oracles
LLaVA-OV [ 3 ]	0.74	5.93	5.73
Idefics3 [ 39 ]	0.80	9.84	29.21
Qwen2.5VL [ 5 ]	0.83	10.16	2.34

Table 2: Comparison with state-of-the-art models. MemFeed performance of Ay MemCoach when comparing to several Ay teacher oracle , Ay zero-shot and Ay aesthetics specialized MLLMs. MemCoach achieves the best results in the considered metrics. Best results in bold .

Model	Editing		Perplexity ( $\downarrow$ )
Model	IR ( $\uparrow$ )	RM% ( $\uparrow$ )	Perplexity ( $\downarrow$ )
LLaVA-OV [ 3 ]	0.70	5.87	7.58
MemCoach- LLaVA	0.73 (+4.29%)	5.04 (-14.14%)	14.05 (+85.36%)
Idefics3 [ 39 ]	0.73	6.64	20.19
MemCoach- Idefics	0.75 (+2.74%)	6.69 (+0.75%)	19.81 (-1.88%)
Qwen2.5VL [ 5 ]	0.68	4.26	10.23

Table 3: Generalization to different MLLMs. MemFeed performance of Ay MemCoach when applied to different architectures. MemCoach generalizes to different models, enhancing their ability to produce memorability feedback.

Figure 6: Common feedback patterns on source images. MemCoach favors symmetric and socially connected compositions, reflecting principles of human photography.

Figure 7: Qualitative feedback from MemCoach. For each source image (left), the model provides natural-language feedback (bottom) that is applied to produce the destination image (right). Each score represents the Relative Memorability (RM), indicating how suggested feedback affects memorability. MemCoach provides human-interpretable and actionable feedback that translates into semantic changes for overall improved memorability. Observed failure cases propose to remove out-of-context elements.

Model	Editing		Perplexity ( $\downarrow$ )
Model	IR ( $\uparrow$ )	RM% ( $\uparrow$ )	Perplexity ( $\downarrow$ )
Qwen-contrasting	0.73	5.68	5.13
Diff(Mean)	0.78	6.64	4.39
MemCoach (Ours)	0.80	7.21	4.99

Table 4: Ablation analysis. MemFeed performance of Ay MemCoach when ablating on the contrasting data teacher and steering vector computation.

Figure 8: Data efficiency. Top: performance vs number of training/contrasting samples. Bottom: performance vs coefficient

\alpha

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Model	Fts dim	Normalization	Spearman Rank ( $\uparrow$ )
Human*	n.d.	n.d.	0.68
ViT-L-14-quickgelu	768	✓	0.73
ViT-L-14-quickgelu	768	$\times$	0.81
ViT-SO400M-14-SigLIP-384	1152	✓	0.76
MemBench $\mathcal{M}$	1152	$\times$	0.82

Appendix

Table 5: Model

\mathcal{M}

performance. Comparison of memorability predictor models trained on CLIP-like embeddings. We report feature dimensionality, whether feature normalization is applied, and Spearman’s rank correlation. The Ay used predictor model achieves the highest correlation among all evaluated variants. (*) is reported from [ 74 ] .

Model	Pretrained	Spearman Rank ( $\uparrow$ )
MemNet* [ 63 ]	LaMem	0.64
AMNet* [ 17 ]	LaMem	0.67
Human*	n.d.	0.68
ViTMem* [ 21 ]	LaMem	0.71
Henry [ 58 ]	LaMem + MemCat + SUN	0.72
Henry [ 58 ]	LaMem	0.74

Appendix

Table 6: Comparison with state-of-the-art memorability predictors. Spearman Rank correlation on the LaMem test set. Our model, trained on LaMem, MemCat, and SUN, achieves the highest correlation among all methods. (*) is reported from [ 74 ] .

Model	Layer	Coefficient	LM Depth	IR
MemCoach- Idefics	13	30	32	0.75
MemCoach- LLaVA	20	143	28	0.73
MemCoach- Qwen	12	26	28	0.74
MemCoach- InternVL	12	55	36	0.80

Appendix

Table 7: Optimal steering configuration across models. Best-performing layer index

l

and steering coefficient

\alpha

obtained via hyperparameter tuning for each evaluated open-source multimodal model. We also report the language-model depth (LM Depth) and the corresponding IR score.

Figure 9: Human memory performance across three different image settings.

Model	Clearness	Relevance	Feasibility
Oracle	4.19	4.30	4.11
MemCoach	3.96	3.76	4.32

Appendix

Table 8: Feedback quality results.

Model	Edit Model		Mem Predictor
Model	Qwen-IE	FLUX.2-k	VM	VM $\rightarrow$ MB
Edit model	0.69	0.68	0.64	0.69
Zero-shot baselines
GPT-5-Mini	0.78	0.80	0.73	0.76
LLaVA-OV	0.59	0.68	0.76	0.71
Idefics3	0.69	0.68	0.73	0.73

Appendix

Table 9: Performance of our framework on different settings . We report the results using different editing models for the evaluation and different memorability predictors.

Panel of Figure 10 — Figure 10: A set of qualitative examples from MemBench.

Panel of Figure 11 — Figure 11: A set of qualitative examples from MemBench.

Personal Visual Memory from Explicit and Implicit Evidence
May 27, 2026Viet Nguyen, Thao Nguyen, Vishal M. Patel +1Multimodal Memory AI Agent Benchmarks
Johns Hopkins University · University of Wisconsin-Madison · Adobe Research
Decide Before You Look: Learning Which Retrieved Memories Deserve Pixels
Oct 6, 2026Youxing LIMemory-Augmented VLMs Efficient Multimodal Inference
The Chinese University of Hong Kong
CUE-Mem: Benchmarking Long-Term User Memory via Implicit Cues in Multimodal Conversations
Sep 26, 2026Yulin Hu, Yanyan Zhao, Zimo Long +6Multimodal Memory Memory Agent Benchmarks
Harbin Institute of Technology · Huawei Technologies Co., Ltd.

May 27, 2026J/K move · Enter open · S save

Personal Visual Memory from Explicit and Implicit Evidence

Viet Nguyen, Thao Nguyen, Vishal M. Patel, Yuheng Li

Johns Hopkins University · University of Wisconsin-Madison · Adobe Research

Multimodal Memory AI Agent Benchmarks Long-Term Conversational Memory Memory-Augmented Agents

Open paper AskPDF arXiv

Long-term memory is increasingly important for personalized AI agents, yet existing benchmarks and methods remain largely text-centric. Even when images are included, the user-specific information needed for later questions is typically recoverable from text alone, and most memory systems reduce image turns to generic captions. Yet images often carry personal information that text rarely states -- both explicit evidence, such as recurring user-associated entities, and implicit evidence, such as latent user facts inferred from visual or multimodal cues. We introduce a benchmark for personal visual memory that targets both forms of evidence, and propose VisualMem, a hybrid visual--text architecture that augments a text-memory backend with a structured personal visual memory module. Rather than collapsing images into captions, VisualMem uses conversational context to resolve identity, ownership, and durable user facts. Experiments show that VisualMem substantially outperforms prior memory systems on our benchmark while remaining competitive on standard text-memory benchmarks, indicating that personal visual memory is a distinct and important component of long-term memory for personalized AI agents.

Abstract

Explore similar work

Personal Visual Memory from Explicit and Implicit Evidence

Decide Before You Look: Learning Which Retrieved Memories Deserve Pixels

CUE-Mem: Benchmarking Long-Term User Memory via Implicit Cues in Multimodal Conversations