Newest papers

DISTRACT: Degradation-Indexed Study of Textual Reference Across Competing Targets

Dan Zlotnikov, Ohad Ben‐Shahar · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28419 · cited by 0 works (OpenAlex) · open-access PDF

Korean

시각적 측정 행동 추적기(VLTs)는 추적을 지원하기 위한 설명을 받아들이지만 텍스트를 받아들이는 것은 시각적 증거가 악화될 때 특히 시각적 측정 결정을 변경하는 내용을 입증하지는 않는다. 우리는 비디오, 목표 및 방해자를 고정시키는 맞춤형 개입 벤치마크인 DISTRACT를 도입합니다. 비디오, 목표 및 방해자를 고정시키는 동안 네 개의 텍스트 프리어를 통제된 심각성 축을 따라 네 개의 이미지 진화로 교차합니다. UVLTrack, MMTrack, DUTrack는 4 개의 데이터 세트를 사용하여 행동 대조, 레이어 비주얼 프레젠테이션 검사 및 활성화 패치를 사용하여 다섯 개의 VLT를 평가합니다.

Machine translation (Meta M2M100); the English original follows.

Abstract

Vision-language trackers (VLTs) accept descriptions intended to assist tracking, but accepting text does not establish that its content changes tracking decisions, particularly as visual evidence deteriorates. We introduce DISTRACT, a matched-intervention benchmark that holds video, target, and distractor fixed while crossing four text priors with four image degradations along a controlled severity axis. We evaluate five VLTs on four datasets using behavioral contrasts, layerwise representation probes, and activation patching. Molmo2 and JointNLT exhibit directed text use. Some effects contract under degradation, whereas others show no significant endpoint change after multiplicity correction. UVLTrack, MMTrack, and DUTrack respond only weakly to changes in text semantics, with no directed behavioral effect surviving FDR correction in the tested settings. Model-internal analyses reveal that at decision-near states, correct-versus-conflicting text is decodable in Molmo2 and JointNLT but not in the other three systems. In the responsive models, decodability peaks at late states where replacement produces little behavioral change, whereas replacing selected earlier states redirects conflict-associated trajectories toward the target. Because matched-correct donors do not significantly outperform unrelated donors, these interventions identify earlier intervention-sensitive states without establishing target-specific semantic rescue. DISTRACT thus exposes when and where text affects tracking under degraded visual evidence.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Eye tracking, Representation (politics), BitTorrent tracker, Artificial intelligence, Benchmark (surveying)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange