English
Related papers

Related papers: GIFT: Global Irreplaceability Frame Targeting for …

200 papers

Long-form video question answering requires reasoning over extended temporal contexts, making frame selection critical for large vision-language models (LVLMs) bound by finite context windows. Existing methods face a sharp trade-off:…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Dan Ben-Ami , Gabriele Serussi , Kobi Cohen , Chaim Baskin

Video diffusion models lack explicit geometric supervision during training, leading to inconsistency artifacts such as object deformation, spatial drift, and depth violations in generated videos. To address this limitation, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Tengjiao Yin , Jinglei Shi , Heng Guo , Xi Wang

Visual instruction tuning has become the predominant technology in eliciting the multimodal task-solving capabilities of large vision-language models (LVLMs). Despite the success, as visual instructions require images as the input, it would…

Computation and Language · Computer Science 2025-02-18 Zikang Liu , Kun Zhou , Wayne Xin Zhao , Dawei Gao , Yaliang Li , Ji-Rong Wen

Recently, large language models (LLMs) have demonstrated impressive capabilities in dealing with new tasks with the help of in-context learning (ICL). In the study of Large Vision-Language Models (LVLMs), when implementing ICL, researchers…

Computation and Language · Computer Science 2024-12-11 Ellen Yi-Ge , Jiechao Gao , Wei Han , Wei Zhu

Despite the impressive advancements of Large Vision-Language Models (LVLMs), existing approaches suffer from a fundamental bottleneck: inefficient visual-language integration. Current methods either disrupt the model's inherent structure or…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Tongtian Yue , Longteng Guo , Yepeng Tang , Zijia Zhao , Xinxin Zhu , Hua Huang , Jing Liu

Vision-language pre-training has significantly elevated performance across a wide range of image-language applications. Yet, the pre-training process for video-related tasks demands exceptionally large computational and data resources,…

Computer Vision and Pattern Recognition · Computer Science 2024-04-30 Lin Xu , Yilin Zhao , Daquan Zhou , Zhijie Lin , See Kiong Ng , Jiashi Feng

Tool use requires reasoning about the fit between an object's affordances and the demands of a task. Visual affordance learning can benefit from goal-directed interaction experience, but current techniques rely on human labels or expert…

Robotics · Computer Science 2021-06-30 Dylan Turpin , Liquan Wang , Stavros Tsogkas , Sven Dickinson , Animesh Garg

Recent advances have shown that large-scale video diffusion models can be repurposed as neural renderers by first decomposing videos into intrinsic scene representations and then performing forward rendering under novel illumination. While…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Weiqing Xiao , Hong Li , Xiuyu Yang , Houyuan Chen , Wenyi Li , Tianqi Liu , Shaocong Xu , Chongjie Ye , Hao Zhao , Beibei Wang

Recent advances in image generation have led to the widespread availability of highly realistic synthetic media, increasing the difficulty of reliable deepfake detection. A key challenge is generalization, as detectors trained on a narrow…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Yichen Jiang , Mohammed Talha Alam , Sohail Ahmed Khan , Duc-Tien Dang-Nguyen , Fakhri Karray

Video moment retrieval (VMR) aims to locate the most likely video moment(s) corresponding to a text query in untrimmed videos. Training of existing methods is limited by the lack of diverse and generalisable VMR datasets, hindering their…

Computer Vision and Pattern Recognition · Computer Science 2025-02-24 Dezhao Luo , Shaogang Gong , Jiabo Huang , Hailin Jin , Yang Liu

Inspired by the remarkable success of Latent Diffusion Models (LDMs) for image synthesis, we study LDM for text-to-video generation, which is a formidable challenge due to the computational and memory constraints during both model training…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Jiaxi Gu , Shicong Wang , Haoyu Zhao , Tianyi Lu , Xing Zhang , Zuxuan Wu , Songcen Xu , Wei Zhang , Yu-Gang Jiang , Hang Xu

Unified video models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vision-language models (VLMs). We attribute this gap to two…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Xinyu Liu , Hangjie Yuan , Yujie Wei , Jiazheng Xing , Yujin Han , Jiahao Pan , Yanbiao Ma , Chi-Min Chan , Kang Zhao , Shiwei Zhang , Wenhan Luo , Yike Guo

Video super-resolution aims at generating a high-resolution video from its low-resolution counterpart. With the rapid rise of deep learning, many recently proposed video super-resolution methods use convolutional neural networks in…

Computer Vision and Pattern Recognition · Computer Science 2020-01-07 Xiaohong Liu , Lingshi Kong , Yang Zhou , Jiying Zhao , Jun Chen

The rapid increase in the amount of published visual data and the limited time of users bring the demand for processing untrimmed videos to produce shorter versions that convey the same information. Despite the remarkable progress that has…

Computer Vision and Pattern Recognition · Computer Science 2020-04-01 Washington Ramos , Michel Silva , Edson Araujo , Leandro Soriano Marcolino , Erickson Nascimento

Video-language modeling has attracted much attention with the rapid growth of web videos. Most existing methods assume that the video frames and text description are semantically correlated, and focus on video-language modeling at video…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Haoyu Lu , Mingyu Ding , Nanyi Fei , Yuqi Huo , Zhiwu Lu

Without incurring significant computational overhead, train-free long video generation aims to enable foundation video generation models to produce longer videos. Frame-level autoregressive frameworks, e.g., FIFO-diffusion, offer the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 X. Feng , J. Zhu , M. Wu , C. Chen , F. Mao , H. Guo , J. Wu , X. Chu , K. Huang

In recent times, Vision-Language Models (VLMs) have been trained under two predominant paradigms. Generative training has enabled Multimodal Large Language Models (MLLMs) to tackle various complex tasks, yet issues such as hallucinations…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Wei Chow , Juncheng Li , Qifan Yu , Kaihang Pan , Hao Fei , Zhiqi Ge , Shuai Yang , Siliang Tang , Hanwang Zhang , Qianru Sun

Screening tasks that aim to identify a small subset of top alternatives from a large pool are common in business decision-making processes. These tasks often require substantial human effort to evaluate each alternative's performance,…

Machine Learning · Statistics 2025-04-28 Zaile Li , Weiwei Fan , L. Jeff Hong

Action recognition is computationally expensive. In this paper, we address the problem of frame selection to improve the accuracy of action recognition. In particular, we show that selecting good frames helps in action recognition…

Computer Vision and Pattern Recognition · Computer Science 2020-12-22 Shreyank N Gowda , Marcus Rohrbach , Laura Sevilla-Lara

Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding…

Computer Vision and Pattern Recognition · Computer Science 2024-10-03 Hongchen Wei , Zhenzhong Chen