Papers › VidCtx: Context-aware Video Question Answering with Image Models

VidCtx: Context-aware Video Question Answering with Image Models

23 Dec 2024arXiv:2412.17415archive 2025-07-28

Andreas Goulas, Vasileios Mezaris, Ioannis Patras

To address computational and memory limitations of Large Multimodal Models in the Video Question-Answering task, several recent methods extract textual representations per frame (e.g., by captioning) and feed them to a Large Language Model (LLM) that processes them to produce the final response. However, in this way, the LLM does not have access to visual information and often has to process repetitive textual descriptions of nearby frames. To address those shortcomings, in this paper, we introduce VidCtx, a novel training-free VideoQA framework which integrates both modalities, i.e. both visual information from input frames and textual descriptions of others frames that give the appropriate context. More specifically, in the proposed framework a pre-trained Large Multimodal Model (LMM) is prompted to extract at regular intervals, question-aware textual descriptions (captions) of video frames. Those will be used as context when the same LMM will be prompted to answer the question at hand given as input a) a certain frame, b) the question and c) the context/caption of an appropriate frame. To avoid redundant information, we chose as context the descriptions of distant frames. Finally, a simple yet effective max pooling mechanism is used to aggregate the frame-level decisions. This methodology enables the model to focus on the relevant segments of the video and scale to a high number of frames. Experiments show that VidCtx achieves competitive performance among approaches that rely on open models on three public Video QA benchmarks, NExT-QA, IntentQA and STAR. Our code is available at https://github.com/IDT-ITI/VidCtx.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

idt-iti/vidctx officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Large Language ModelQuestion AnsweringVideo Question AnsweringZero-Shot Video Question Answer

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Zero-Shot Video Question Answer IntentQA VidCtx (7B) Accuracy 67.1 #4 of 13 Archive leaderboard report
Zero-Shot Video Question Answer NExT-QA VidCtx (7B) Accuracy 70.7 #10 of 27 Archive leaderboard report
Zero-Shot Video Question Answer STAR Benchmark VidCtx (7B) Accuracy 51.1 #2 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

FocusMax Pooling

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections