CORTEXA
← Browse
arxivcs.CV2026-07-10Cited by 0

Semantic Hardness Is Not Visual Hardness: Sign-Aware Hard Negative Mining for Sign Language Retrieval

Junmyeong Lee, Chan Hur, ChangSu Choi, Sukmin Cho, Fitsum Gaim, Eui Jun Hwang, Hoyun Song, KyungTae Lim

Sign Language Retrieval (SLRet) enables efficient access to sign language content but remains fragile in fine-grained scenarios where visually similar signs must be distinguished. We show that this limitation does not stem from model capacity, but from ineffective hard negative supervision. Specifically, we formulate fine-grained retrieval failures as a negative distribution mismatch: semantically distinct yet visually confusable signs are rarely treated as hard negatives, while existing text-based mining strategies fail to capture such visual ambiguity. To address this issue, we propose Sign-Aware Hard Negative Mining (SAN), which constructs hard negatives based on visual confusability in the sign embedding space rather than linguistic similarity. Experiments on PHOENIX-2014T demonstrate that SAN substantially improves fine-grained retrieval performance while preserving coarse-grained accuracy, highlighting the importance of aligning negative supervision with visual ambiguity in sign language retrieval.

View free PDFSource page

Related papers

arxivcs.CV2026-06-26

SIGNET: Motion-Level Knowledge Transfer for Cross-Language Sign Language Translation

Sobhan Asasi, Ozge Mercanoglu Sincan, Richard Bowden

Sign language translation (SLT) remains challenging due to its high spatio-temporal complexity, long sequences, and the need to model multiple articulators without relying on gloss annotations. Existing approaches are typically tailored to individual datasets or languages and str…

View free PDFSource page
arxivcs.CVcs.AIcs.CL2026-06-30

Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?

Ta Duc Huy, Trang Nguyen, Townim Chowdhury, Ankit Yadav, Minh-Son To, Zhibin Liao, et al.

Vision-language models can produce confident answers on visually ambiguous inputs, resulting in biased predictions. Common entropy-based methods, such as Semantic Entropy (SE), rely on output diversity. Yet our analysis shows that overconfident visual embeddings suppress output d…

View free PDFSource page
arxivcs.CV2026-07-04

Do Medical Vision Language Models Actually See? A Counterfactual Grounding Framework and Hard-Negative Contrastive Training for Visually-Reliant Medical VLMs

Anas Zafar, Leema Krishna Murali, Siddhant Bharadwaj, Ashish Vashist, Jia Wu

Large vision language models (VLMs) report strong accuracy on medical question-answering, yet it remains unclear whether they reason from visual evidence or exploit textual shortcuts. We introduce a counterfactual evaluation framework that decouples visual and textual contributio…

View free PDFSource page
arxivq-bio.NCcs.AIcs.CVcs.HC2026-07-03

Modeling the Impact of Visual Brand Language on Attention, Object Recognition, and Memory Retrieval

Rachel F. Heaton, John E. Hummel

Visual brand language is the set of visual properties that convey brand identity for a product. What is the impact of visual brand language on a person's ability to recognize and understand the functional identity of an object? Using an empirically supported modeling framework ba…

View free PDFSource page
arxivcs.CVcs.AI2026-07-04

ViPo-MLLM: Visual-Pose Multimodal LLM for Gloss-Free Sign Language Translation

Ahmed Abul Hasanaath, Bicheng Xu, Mir Rayat Imtiaz Hossain, Leonid Sigal, Hamzah Luqman

Gloss-free Sign Language Translation (SLT) translates sign language videos into spoken-language sentences without gloss annotations, avoiding costly labeling but requiring fine-grained modeling of hands, body, and facial cues. Existing methods often use single-modality or weakly…

View free PDFSource page