2026· International Conference on Language Resources and Evaluation· pp. 5024-5034· 0 citations· 19 references
Computer Science
TL;DR
VideoEvent is a lightweight and efficient training-free framework that segments an input video into question-relevant temporal events and selectively supplements them with low-level visual cues such as background and object layout, making it highly suitable for practical deployment.
Frame selection is an important component of long-video question answering (VQA) with Multimodal Large Language Models (MLLMs). Existing frame-selection methods improve over simple top-$k$ embedding retrieval and uniform sampling, but are typically applied under a fixed global selection budget. We introduce \textbf{Met...
This work introduces a frame-selection method designed specifically for multiple-choice questions, and is the first to directly utilize answer choices as inference-time cues for selecting frames relevant to answering a question.
The resulting training-free pipeline, RECAST, consistently outperforms recent frame-selection baselines without modifying the ITM encoder, and preserves the per-frame matching cost of a standard single-query baseline.
S. Han, Thang Vu, Junyeong Kim· IEEE Access· 0 citations
STITCH is presented, a training-free method that divides a video into semantically meaningful temporal chunks that are computed once per video and reused across tasks, suggesting that reusable temporal abstraction is a promising direction for general video understanding.
Etienne Casanova, S. Brodjian, Pietro Perona· 0 citations
Current large video-language models (LVLMs) still face challenges when dealing with long videos, mainly because frames are often processed independently, making it difficult to capture temporal dependencies across events. Although retrieval-augmented approaches have been introduced to provide additional context, most o...
Yu-Hao Qin, Jun-Bo Wang, Yu-Ke Li et al.· 0 citations
This survey covers inference-efficiency mechanisms for visual and audiovisual VideoLLMs that report concrete reductions in parameter count, FLOPs per input, latency, memory, or visual and audio token count, and organize methods by the pipeline stage at which they act.
Killian Steunou, Yannis Tevissen, M. El Yacoubi· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
