English
Related papers

Related papers: GraphThinker: Reinforcing Temporally Grounded Vide…

200 papers

Human perception of events is intrinsically tied to distinguishing between completed (perfect and telic) and ongoing (durative) actions, a process mediated by both linguistic structure and visual cues. In this work, we introduce the…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Olga Loginova , Sofía Ortega Loguinova

Large multimodal reasoning models solve challenging visual problems via explicit long-chain inference: they gather visual clues from images and decode clues into textual tokens. Yet this capability also increases hallucinations, where the…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Gongli Xi , Kun Wang , Zeming Gao , Huahui Yi , Haolang Lu , Ye Tian , Wendong Wang

Video Question Answering (Video QA) is a challenging video understanding task that requires models to comprehend entire videos, identify the most relevant information based on contextual cues from a given question, and reason accurately to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Roberto Amoroso , Gengyuan Zhang , Rajat Koner , Lorenzo Baraldi , Rita Cucchiara , Volker Tresp

Large Multimodal Models (LMMs) have achieved impressive progress in visual perception and reasoning. However, when confronted with visually ambiguous or non-semantic scene text, they often struggle to accurately spot and understand the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-08 Yan Shu , Hangui Lin , Yexin Liu , Yan Zhang , Gangyan Zeng , Yan Li , Yu Zhou , Ser-Nam Lim , Harry Yang , Nicu Sebe

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Binbin Ji , Siddharth Agrawal , Qiance Tang , Yvonne Wu

Fine-tuning MLLMs for Video Temporal Grounding (VTG) often improves in-domain performance but degrades sharply under domain shift. In this work, we find that this failure is primarily driven not just by unseen query concepts, but by visual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Geo Ahn , Jiwook Han , Youngrae Kim , Joonseok Lee , Jinwoo Choi

Video Question Answering (VQA) requires models to reason over spatial, temporal, and causal cues in videos. Recent vision language models (VLMs) achieve strong results but often rely on shallow correlations, leading to weak temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Haodi Ma , Vyom Pathak , Daisy Zhe Wang

Spatio-temporal reasoning is a remarkable capability of Vision Language Models (VLMs), but the underlying mechanisms of such abilities remain largely opaque. We postulate that visual/geometrical and textual representations of spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Raphi Kang , Hongqiao Chen , Georgia Gkioxari , Pietro Perona

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved performance on tasks such as visual grounding and visual question answering. However, the reasoning processes of these models remain largely opaque;…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Haobo Yuan , Yueyi Sun , Yanwei Li , Tao Zhang , Xueqing Deng , Henghui Ding , Lu Qi , Anran Wang , Xiangtai Li , Ming-Hsuan Yang

Video temporal grounding aims to localize relevant temporal boundaries in a video given a textual prompt. Recent work has focused on enabling Video LLMs to perform video temporal grounding via next-token prediction of temporal timestamps.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Xizi Wang , Feng Cheng , Ziyang Wang , Huiyu Wang , Md Mohaiminul Islam , Lorenzo Torresani , Mohit Bansal , Gedas Bertasius , David Crandall

Existing Video Large Language Models (Video LLMs) struggle with complex video understanding, exhibiting limited reasoning capabilities and potential hallucinations. In particular, these methods tend to perform reasoning solely relying on…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Qizhong Tan , Zhuotao Tian , Guangming Lu , Jun Yu , Wenjie Pei

Recent "Thinking with Video" approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reasoning artifacts. Even strong VGMs, however, exhibit two recurring failure modes on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Joowon Kim , Seungho Shin , Joonhyung Park , Eunho Yang

Large Vision-Language Models (LVLMs) achieve strong performance on visual question answering benchmarks, yet often rely on spurious correlations rather than genuine causal reasoning. Existing evaluations primarily assess the correctness of…

Artificial Intelligence · Computer Science 2026-02-25 Dhita Putri Pratama , Soyeon Caren Han , Yihao Ding

In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as graphs and tables, which is typically linearized into sequential token representations. However, even when sufficient knowledge is…

Computation and Language · Computer Science 2026-05-27 Shanghao Li , Jinda Han , Yibo Wang , Yuanjie Zhu , Zihe Song , Langzhou He , Kenan Kamel A Alghythee , Philip S. Yu

Understanding the physical world - governed by laws of motion, spatial relations, and causality - poses a fundamental challenge for multimodal large language models (MLLMs). While recent advances such as OpenAI o3 and GPT-4o demonstrate…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Zhuobai Dong , Junchao Yi , Ziyuan Zheng , Haochen Han , Xiangxi Zheng , Alex Jinpeng Wang , Fangming Liu , Linjie Li

Multimodal reasoning with large language models (LLMs) often suffers from hallucinations and the presence of deficient or outdated knowledge within LLMs. Some approaches have sought to mitigate these issues by employing textual knowledge…

Computation and Language · Computer Science 2024-06-06 Junlin Lee , Yequan Wang , Jing Li , Min Zhang

Large Vision-Language Models (LVLMs) have advanced rapidly by aligning visual patches with the text embedding space, but a fixed visual-token budget forces images to be resized to a uniform pretraining resolution, often erasing fine-grained…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Zipeng Zhu , Zhanghao Hu , Qinglin Zhu , Yuxi Hong , Yijun Liu , Jingyong Su , Yulan He , Lin Gui

Large language models (LLMs) excel at retrieving information from lengthy text, but their vision-language counterparts (VLMs) face difficulties with hour-long videos, especially for temporal grounding. Specifically, these VLMs are…

Computer Vision and Pattern Recognition · Computer Science 2024-11-25 Tanveer Hannan , Md Mohaiminul Islam , Jindong Gu , Thomas Seidl , Gedas Bertasius

While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning remains a widely open problem. In this…

Machine Learning · Computer Science 2025-09-11 Mohamed Salim Aissi , Clemence Grislain , Mohamed Chetouani , Olivier Sigaud , Laure Soulier , Nicolas Thome

Recently, Multimodal Large Language Models (MLLMs) have demonstrated significant potential in complex visual tasks through the integration of Chain-of-Thought (CoT) reasoning. However, in Video Question Answering, extended thinking…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Xiaokun Sun , Yubo Wang , Haoyu Cao , Linli Xu