English
Related papers

Related papers: HORNet: Task-Guided Frame Selection for Video Ques…

200 papers

Accurate video moment retrieval (VMR) requires universal visual-textual correlations that can handle unknown vocabulary and unseen scenes. However, the learned correlations are likely either biased when derived from a limited amount of…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Dezhao Luo , Jiabo Huang , Shaogang Gong , Hailin Jin , Yang Liu

Recent Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Qiankun Ma , Ziyao Zhang , Haofei Wang , Jie Chen , Zhen Song , Hairong Zheng

Recent breakthroughs in computer vision and natural language processing have spurred interest in challenging multi-modal tasks such as visual question-answering and visual dialogue. For such tasks, one successful approach is to condition…

Computer Vision and Pattern Recognition · Computer Science 2018-10-15 Florian Strub , Mathieu Seurin , Ethan Perez , Harm de Vries , Jérémie Mary , Philippe Preux , Aaron Courville , Olivier Pietquin

Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered by a "visual processing bottleneck": a propensity to lose grounding in visual evidence and exhibit a…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Xinlei Yu , Chengming Xu , Guibin Zhang , Zhangquan Chen , Yudong Zhang , Yongbo He , Peng-Tao Jiang , Jiangning Zhang , Xiaobin Hu , Shuicheng Yan

Recent Vision-Language-Action (VLA) models equipped with Flow Matching (FM) action heads achieve state-of-the-art performance in complex robot manipulation. However, the multi-step iterative ODE solving required by FM introduces inference…

Robotics · Computer Science 2026-03-19 Zhou Fang , Jiaqi Wang , Yi Zhou , Qiongfeng Shi

Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time visual assistants. Existing VLM frameworks predominantly assess…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Pavan Kumar Anasosalu Vasu , Cem Koc , Fartash Faghri , Chun-Liang Li , Bo Feng , Zhengfeng Lai , Meng Cao , Oncel Tuzel , Hadi Pouransari

Multimodal large language models (LLMs) have made rapid progress in visual understanding, yet their extension from images to videos often reduces to a naive concatenation of frame tokens. In this work, we investigate what video finetuning…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Ruiqi Yang , Tian Yun , Zihan Wang , Ellie Pavlick

Current Multimodal Large Language Models (MLLMs) may struggle with understanding long or complex videos due to computational demands at test time, lack of robustness, and limited accuracy, primarily stemming from their feed-forward…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Jiahao Meng , Shuyang Sun , Yue Tan , Lu Qi , Yunhai Tong , Xiangtai Li , Longyin Wen

Vision-Language-Action (VLA) models fail systematically on long-horizon manipulation tasks despite strong short-horizon performance. We show that this failure is not resolved by extending context length alone in the current reactive…

Machine Learning · Computer Science 2026-04-22 Zijian Zeng , Fei Ding , Huiming Yang , Xianwei Li

In recent years, advances in Artificial Intelligence have significantly impacted computer science, particularly in the field of computer vision, enabling solutions to complex problems such as video frame prediction. Video frame prediction…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Jose M. Sánchez Velázquez , Mingbo Cai , Andrew Coney , Álvaro J. García- Tejedor , Alberto Nogales

Video Large Language Models (Video-LLMs) are improving rapidly, yet current Video Question Answering (VideoQA) benchmarks often admit single-cue shortcuts, under-testing reasoning that must integrate evidence across time. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Dan Ben-Ami , Gabriele Serussi , Kobi Cohen , Chaim Baskin

Situational awareness applications rely heavily on real-time processing of visual and textual data to provide actionable insights. Vision language models (VLMs) have become essential tools for interpreting complex environments by connecting…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Md Azim Khan , Aryya Gangopadhyay , Jianwu Wang , Robert F. Erbacher

Video quality is a primary concern for video service providers. In recent years, the techniques of video quality assessment (VQA) based on deep convolutional neural networks (CNNs) have been developed rapidly. Although existing works…

Image and Video Processing · Electrical Eng. & Systems 2022-10-11 Ao-Xiang Zhang , Yuan-Gen Wang , Weixuan Tang , Leida Li , Sam Kwong

Visual reasoning models (VRMs) have recently shown strong cross-modal reasoning capabilities by integrating visual perception with language reasoning. However, they often suffer from overthinking, producing unnecessarily long reasoning…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Yixu Huang , Tinghui Zhu , Muhao Chen

In video captioning task, the best practice has been achieved by attention-based models which associate salient visual components with sentences in the video. However, existing study follows a common procedure which includes a frame-level…

Computer Vision and Pattern Recognition · Computer Science 2018-03-06 Yangyu Chen , Shuhui Wang , Weigang Zhang , Qingming Huang

Vision-Language models (VLMs) that use contrastive language-image pre-training have shown promising zero-shot classification performance. However, their performance on imbalanced dataset is relatively poor, where the distribution of classes…

Artificial Intelligence · Computer Science 2023-06-22 Yidong Wang , Zhuohao Yu , Jindong Wang , Qiang Heng , Hao Chen , Wei Ye , Rui Xie , Xing Xie , Shikun Zhang

Vision-Language Models (VLMs) have demonstrated remarkable capabilities in interpreting visual layouts and text. However, a significant challenge remains in their ability to interpret robustly and reason over multi-tabular data presented as…

Computer Vision and Pattern Recognition · Computer Science 2025-06-16 Anshul Singh , Chris Biemann , Jan Strich

Fine-grained supervision based on object annotations has been widely used for vision and language pre-training (VLP). However, in real-world application scenarios, aligned multi-modal data is usually in the image-caption format, which only…

Computer Vision and Pattern Recognition · Computer Science 2023-05-09 Lisai Zhang , Qingcai Chen , Zhijian Chen , Yunpeng Han , Zhonghua Li , Zhao Cao

Recent developments in vision language models (VLM) have shown great potential for diverse applications related to image understanding. In this study, we have explored state-of-the-art VLM models for vision-based transportation engineering…

Computer Vision and Pattern Recognition · Computer Science 2024-09-05 Sanjita Prajapati , Tanu Singh , Chinmay Hegde , Pranamesh Chakraborty

Vision Language Models (VLMs) are impressive at visual question answering and image captioning. But they underperform on multi-step visual reasoning -- even compared to LLMs on the same tasks presented in text form -- giving rise to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Simon Park , Abhishek Panigrahi , Yun Cheng , Dingli Yu , Anirudh Goyal , Sanjeev Arora