English
Related papers

Related papers: CONE: An Efficient COarse-to-fiNE Alignment Framew…

200 papers

Long-form video understanding is essential for various applications such as video retrieval, summarizing, and question answering. Yet, traditional approaches demand substantial computing power and are often bottlenecked by GPU memory. To…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Saket Gurukar , Asim Kadav

Video-language models (VLMs) face rapid inference costs as visual token counts scale with video length. For example, 32 frames at $448{\times}448$ resolution already yield >8,000 visual tokens in Qwen3-VL, making LLM prefill the dominant…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Simin Huo , Ning LI

Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens or hundreds of tokens, the limited context length of large…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Zheyu Zhang , Ziqi Pang , Shixing Chen , Xiang Hao , Vimal Bhat , Yu-Xiong Wang

Query-based moment retrieval aims to localize the most relevant moment in an untrimmed video according to the given natural language query. Existing works often only focus on one aspect of this emerging task, such as the query…

Information Retrieval · Computer Science 2019-07-30 Zhu Zhang , Zhijie Lin , Zhou Zhao , Zhenxin Xiao

The recent advancement in video temporal grounding (VTG) has significantly enhanced fine-grained video understanding, primarily driven by multimodal large language models (MLLMs). With superior multimodal comprehension and reasoning…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Jianlong Wu , Wei Liu , Ye Liu , Meng Liu , Liqiang Nie , Zhouchen Lin , Chang Wen Chen

Large-scale video-language pre-training has shown significant improvement in video-language understanding tasks. Previous studies of video-language pretraining mainly focus on short-form videos (i.e., within 30 seconds) and sentences,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Yuchong Sun , Hongwei Xue , Ruihua Song , Bei Liu , Huan Yang , Jianlong Fu

Temporal video alignment aims to synchronize the key events like object interactions or action phase transitions in two videos. Such methods could benefit various video editing, processing, and understanding tasks. However, existing…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Ishan Rajendrakumar Dave , Fabian Caba Heilbron , Mubarak Shah , Simon Jenni

The task of temporally grounding language queries in videos is to temporally localize the best matched video segment corresponding to a given language (sentence). It requires certain models to simultaneously perform visual and linguistic…

Computer Vision and Pattern Recognition · Computer Science 2019-12-19 Jingwen Wang , Lin Ma , Wenhao Jiang

The remarkable natural language understanding, reasoning, and generation capabilities of large language models (LLMs) have made them attractive for application to video understanding, utilizing video tokens as contextual input. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Jiaqi Xu , Cuiling Lan , Wenxuan Xie , Xuejin Chen , Yan Lu

Visual token compression is widely used to accelerate large vision-language models (LVLMs) by pruning or merging visual tokens, yet its adversarial robustness remains unexplored. We show that existing encoder-based attacks cannot fully…

Cryptography and Security · Computer Science 2026-05-19 Xinwei Zhang , Hangcheng Liu , Li Bai , Hao Wang , Qingqing Ye , Tianwei Zhang , Haibo Hu

Recent multimodal large language models (MLLMs) have advanced video understanding, yet most still "think about videos" ie once a video is encoded, reasoning unfolds entirely in text, treating visual input as a static context. This passive…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Hanoona Rasheed , Mohammed Zumri , Muhammad Maaz , Ming-Hsuan Yang , Fahad Shahbaz Khan , Salman Khan

Recent advances in text-to-video generation have achieved impressive performance on short clips, yet evaluating long-form generation under complex textual inputs remains a significant challenge. In response to this challenge, we present…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Xiangqing Zheng , Chengyue Wu , Kehai Chen , Min Zhang

Large language models (LLMs) have demonstrated exceptional capabilities in text understanding, which has paved the way for their expansion into video LLMs (Vid-LLMs) to analyze video data. However, current Vid-LLMs struggle to…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Ming Nie , Dan Ding , Chunwei Wang , Yuanfan Guo , Jianhua Han , Hang Xu , Li Zhang

Temporal awareness is essential for video large language models (LLMs) to understand and reason about events within long videos, enabling applications like dense video captioning and temporal video grounding in a unified system. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Andong Deng , Zhongpai Gao , Anwesa Choudhuri , Benjamin Planche , Meng Zheng , Bin Wang , Terrence Chen , Chen Chen , Ziyan Wu

Video temporal grounding (VTG) is a critical task in video understanding and a key capability for extending video large language models (Vid-LLMs) to broader applications. However, existing Vid-LLMs rely on uniform frame sampling to extract…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Rong Fan , Kaiyan Xiao , Minghao Zhu , Liuyi Wang , Kai Dai , Zhao Yang

A key solution to temporal sentence grounding (TSG) exists in how to learn effective alignment between vision and language features extracted from an untrimmed video and a sentence description. Existing methods mainly leverage vanilla soft…

Computer Vision and Pattern Recognition · Computer Science 2021-09-15 Daizong Liu , Xiaoye Qu , Pan Zhou

Temporal grounding, also known as video moment retrieval, aims at locating video segments corresponding to a given query sentence. The compositional nature of natural language enables the localization beyond predefined events, posing a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Zixu Cheng , Yujiang Pu , Shaogang Gong , Parisa Kordjamshidi , Yu Kong

This work proposes a new end-to-end DCNN based approach for motion segmentation, especially for video sequences captured with such non-static cameras, called MOSNET. While other approaches focus on spatial or temporal context only, the…

Computer Vision and Pattern Recognition · Computer Science 2021-02-23 Markus Bosch

Spatio-temporal video grounding (or STVG) task aims at locating a spatio-temporal tube for a specific instance given a text query. Despite advancements, current methods easily suffer the distractors or heavy object appearance variations in…

Computer Vision and Pattern Recognition · Computer Science 2024-01-04 Xin Gu , Heng Fan , Yan Huang , Tiejian Luo , Libo Zhang

This paper addresses temporal sentence grounding. Previous works typically solve this task by learning frame-level video features and align them with the textual information. A major limitation of these works is that they fail to…

Computer Vision and Pattern Recognition · Computer Science 2022-01-04 Daizong Liu , Xiaoye Qu , Pan Zhou , Yang Liu