paper-with-me

Papers

Clapper: Compact Learning and Video Representation in VLMs

2025-05-21 · Lingyu Kong, Hongzhi Zhang, Jingyuan Zhang, Jianzhao Huang, Kunze Li, Qi Wang, Fuzheng Zhang

Current vision-language models (VLMs) have demonstrated remarkable capabilities across diverse video understanding applications. Designing VLMs for video inputs requires effectively modeling the temporal dimension (i.e. capturing dependencies across frames) and balancing the processing of short and long videos. Specifically, short videos demand preservation of fine-grained details, whereas long videos require strategic compression of visual information to handle extensive temporal contexts efficiently. However, our empirical analysis reveals a critical limitation: most existing VLMs suffer severe performance degradation in long video understanding tasks when compressing visual tokens below a quarter of their original visual tokens. To enable more effective modeling of both short and long video inputs, we propose Clapper, a method that utilizes a slow-fast strategy for video representation and introduces a novel module named TimePerceiver for efficient temporal-spatial encoding within existing VLM backbones. By using our method, we achieves 13x compression of visual tokens per frame (averaging 61 tokens/frame) without compromising QA accuracy. In our experiments, Clapper achieves 62.0% on VideoMME, 69.8% on MLVU, and 67.4% on TempCompass, all with fewer than 6,000 visual tokens per video. The code will be publicly available on the homepage.

📄 PDF Abstract BibTeX arXiv:2505.15529

Code (0)

등록된 구현이 없습니다.

Tasks

Video Understanding

Similar Papers 제목 키워드 기반

ClapperText: A Benchmark for Text Recognition in Low-Resource Archival Documents

2025-10-17 · Tingyu Lin, Marco Peer, Florian Kleber, Robert Sablatnig arxiv

This paper presents ClapperText, a benchmark dataset for handwritten and printed text recognition in visually degraded and low-resource settings. The dataset is derived from 127 World War II-era archival video segments c…

Few-Shot Learning

CodecCap: High-Fidelity Codec-Inspired Residual Modeling for Dense Video Captioning

2026-05-26 · Zihan Lin, Songhe Deng, Shuwei He, Danxiang Zhu 외 arxiv

Existing video captioning methods struggle to balance visual fidelity and redundancy: holistic captions are compact but lose fine-grained evidence, whereas segment-wise captions improve coverage but introduce heavy redun…

Dense Video CaptioningDense Captioning

SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models

2026-05-13 · Vladislav Makarov, Mark Gizetdinov, Dmitry Yudin arxiv

Scene graph generation provides a compact structured representation for visual perception, but accurate and fast graph prediction from images and videos remains challenging. Recent VLM-based methods can generate scene gr…

Video scene graph generationReinforcement Learning

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

2024-10-06 · Yuan Zhang, Chun-Kai Fan, Junpeng Ma, Wenzhao Zheng 외

In vision-language models (VLMs), visual tokens usually consume a significant amount of computational overhead, despite their sparser information density compared to text tokens. To address this, most existing methods le…

Language ModelingLanguage ModellingVideo Understanding

Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment

2026-05-08 · Jerry Jiang, Haowen Sun, Denis Gudovskiy, Yohei Nakata 외 arxiv

Spatial intelligence in vision-language models (VLMs) attracts research interest with the practical demand to reason in the 3D world.Despite promising results, most existing methods follow the conventional 2D pipeline in…

Visual Question AnsweringScene UnderstandingVisual Grounding