paper-with-me

Papers

Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding

2026-04-16 · Zhixuan Wu, Quanxing Zha, Teng Wang, Genbao Xu, Wenyuan Gu, Wei Rao, Nan Ma, Bo Cheng, Soujanya Poria arxiv

Video understanding requires identifying and reasoning over semantically discriminative visual objects across frames, yet existing object-agnostic solutions struggle to effectively handle substantial object variations over time. To address this, we introduce Chain-of-Glimpse, a search-guided progressive object-grounded reasoning framework that explicitly anchors each reasoning step to specific visual evidence regions, enabling compositional and multi-step decision-making. Formally, Chain-of-Glimpse formulates video reasoning as a step-by-step process that incrementally builds spatially grounded traces around task-relevant visual objects, thereby mitigating over-reliance on saliency-driven cues. Specifically, Chain-of-Glimpse features a search-guided controller, optimized via reinforcement learning with a format reward that significantly incentivizes grounding capability, to iteratively ground visual evidence regions and form reliable reasoning trajectories, yielding accurate and interpretable multi-step decisions. Extensive evaluations on both in domain NExTQA and out-of-domain Video-Holmes, CG-Bench Reasoning, and VRBench benchmarks demonstrate consistent performance gains, robustness and generalization of Chain-of-Glimpse across diverse video reasoning tasks.

📄 PDF Abstract BibTeX arXiv:2604.14692

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition

2021-10-11 · Hossein Adeli, Seoyoung Ahn, Gregory Zelinsky

The visual system processes a scene using a sequence of selective glimpses, each driven by spatial and object-based attention. These glimpses reflect what is relevant to the ongoing task and are selected through recurren…

DecoderObjectObject Recognition

GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction

2022-10-24 · Samrudhdhi B Rangrej, Kevin J Liang, Tal Hassner, James J Clark

Many online action prediction models observe complete frames to locate and attend to informative subregions in the frames called glimpses and recognize an ongoing action based on global and local information. However, in…

Action Recognition

Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes

2022-04-01 · CVPR 2022 1 · Samrudhdhi B. Rangrej, Chetan L. Srinidhi, James J. Clark

Most hard attention models initially observe a complete scene to locate and sense informative glimpses, and predict class-label of a scene based on glimpses. However, in many applications (e.g., aerial imaging), observin…

Hard Attention

Progressive Reasoning with Primitive Correction for Compositional Zero-Shot Learning

2026-07-07 · Ziyi Chen, Haoyan Shi, Sunhan Xu, Congyan Lang arxiv

Compositional Zero-Shot Learning (CZSL) aims to combine known attributes and objects as primitives for recognizing previously unseen attribute-object pairs. Prior works either predict attributes and objects independently…

Compositional Zero-Shot LearningReinforcement Learning

ChainMPQ: Interleaved Text-Image Reasoning Chains for Mitigating Relation Hallucinations

2025-10-07 · Yike Wu, Yiwei Wang, Yujun Cai arxiv

While Large Vision-Language Models (LVLMs) achieve strong performance in multimodal tasks, hallucinations continue to hinder their reliability. Among the three categories of hallucinations, which include object, attribut…

Relational Reasoning