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.ROcs.CV2026-07-22

EA-Nav: Learning Safe Visual Navigation Policies with Embodiment Awareness

Jialu Zhang, Yong Du, Xianda Guo, Shunwang Sun, Xinqi Liu, Yue Sun, et al.

Cross-embodiment navigation is a key challenge in embodied intelligence. Due to differences in embodiment, the same visual observation may imply different actions for different agents, making prediction ambiguous when relying solely on vision. Existing studies mainly rely on rein…

View free PDFSource page
arxivcs.CVcs.AI2026-07-23

CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQA

Hanseok Oh, Parishad BehnamGhader, Benno Krojer, Hyunji Lee, Paul Liang, Siva Reddy, et al.

Knowledge-Intensive Visual Question Answering (KI-VQA) benchmarks evaluate Vision-Language Models (VLMs) as multimodal knowledge assistants by requiring external information beyond a provided image to answer questions. KI-VQA involves multiple sub-problems -referring expression u…

View free PDFSource page
arxivcs.CVcs.AI2026-07-31

QR-Structured Thermal Triggers for Targeted Semantic Attacks on Infrared Vision-Language Models

Xiang Chen, Yingying Zhao, Chao Li, Jiaju Han, Ben Zhang, Ang Li, et al.

Infrared vision-language models (IR-VLMs) extend thermal perception to open-vocabulary classification, image captioning, and visual question answering. However, their robustness to structured thermal perturbations and the stability of cross-modal semantic alignment remain insuffi…

View free PDFSource page