CORTEXA
← Browse
arxivcs.CV2026-07-09

Whareformer: Learning to Track What is Where in Long Egocentric Videos

Jacob Chalk, Saptarshi Sinha, Dima Damen, Yannis Kalantidis, Diane Larlus

The recently established 'Out of Sight, Not out of Mind' (OSNOM) task for egocentric videos focuses on tracking objects that are moved by the camera wearer, online, maintaining knowledge of instance locations throughout the video even when they leave the field of view or become heavily occluded. In this paper, we propose the first learning-based solution to the OSNOM task: Whareformer, a transformer-based model with two components: an updatable memory of established tracks and a track assignment module that associates observations with existing tracks in a feed-forward manner. Whareformer jointly reasons over evolving object appearance (what) and updated 3D location (where), and employs a dedicated New Track token to reason about novel objects. Thanks to its design choices of using relative distances and evolving track representations, Whareformer is trained on a small set of 56 videos but achieves SOTA performance on 260 long test videos from three datasets: EPIC-KITCHENS-100 (unseen videos), IT3DEgo, and HD-EPIC, with significant absolute improvements over prior work.

View free PDFSource page

Related papers

arxivcs.CV2026-07-02

LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension

Shunya Kato, Taiki Miyanishi, Shuhei Kurita, Mahiro Ukai, Nakamasa Inoue, Chenhui Chu

Egocentric videos capture rich and diverse human-object interactions and have emerged as a fundamental resource for understanding human activities related to objects. In this context, Video Referring Expression Comprehension (Video REC), the task of localizing the temporal and sp…

View free PDFSource page
arxivcs.CVcs.AI2026-07-17

Modularized Dynamic-Granularity Video LLM for Multi-Event Long Video Understanding

Wei Feng, Xin Wang, Yu-Wei Zhan, Yuwei Zhou, Wenwu Zhu

Video Large Language Models (Video LLMs) have made significant advancements in various video understanding tasks. However, long-video scenarios remain challenging due to the tension between limited visual token budgets and the need to capture multiple key events. Existing approac…

View free PDFSource page
arxivcs.CV2026-07-01

EFlow: Learning Evidence Flow for Long-Video Reasoning with Adaptive Reflection

Wenhao Zhang, Kuanwei Lin, Xuyi Yang, Wei Gao, Ge Li

Long-video reasoning is fundamentally constrained by how models acquire and utilize visual evidence. Existing tool-augmented video frameworks often interleave temporal grounding and answer reasoning within a single trajectory, causing early semantic hypotheses to bias evidence lo…

View free PDFSource page
arxivcs.CV2026-07-07

ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation

Ruihang Zhang, Felix Taubner, Pooja Ravi, Kiriakos N. Kutulakos, David B. Lindell

Tracking the six-degree-of-freedom (6-DoF) pose of objects and surfaces from monocular video is a long-standing problem in computer vision. To tackle this problem, existing methods require inputs beyond the video itself-such as 3D models, depth maps, object masks, or task-specifi…

View free PDFSource page
arxivcs.CV2026-07-17

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA

Ce Zhang, Ziyang Wang, Yulu Pan, Oluwatumininu Oguntola, Pranav Wagh, Qiyu Wu, et al.

Grounded long-video question answering (Grounded LVQA) requires answering a question about a long video while localizing the short evidence interval that supports the answer. Recent agentic methods frame this task as multi-turn exploration with a single crop_video(start, end) act…

View free PDFSource page
arxivcs.CVcs.LG2026-07-01

MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment

Peiyuan Zhu, Shaoan Xie, Zijian Li, Yifan Shen, Namrata Deka, Harsh Shrivastava, et al.

Contrastive pre-training has propelled video-text alignment, yet models often inherit the critical limitations of their image-text predecessors like CLIP, resulting in entangled representations. These challenges are severely exacerbated by two fundamental properties in the video…

View free PDFSource page