← Back to all news
arXiv AI By Fereshteh Aghaee Meibodi, Amir Mehdi Soufi Enayati, Shadi Alijani, Homayoun Najjaran

Template-Search Domain Adaptation via Multi-Stage Feature Alignment for Cross-Modal Object Tracking

Read the original on arXiv AI →

The paper introduces TSDA-Track, a Template-Search Domain Adaptation framework designed to reduce modality gaps in cross‑modal visual object tracking. Two variants are explored: Pre‑AFA TSDA‑Track uses adversarial alignment before transformer interaction, while Enc‑CFA TSDA‑Track applies contrastive alignment after interaction to strengthen cross‑modal correspondence. Experiments on datasets such as LasHeR, RGBT234, GTOT, and Anti‑UAV‑024 show that both variants outperform state‑of‑the‑art trackers, with Pre‑AFA achieving an SR/PR of 43.2/56.0 on RGBT234 under the modality‑switch protocol.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computer Vision
Sep 25

OptiSAR-Net++: A Large-Scale Benchmark and Transformer-Free Framework for Cross-Domain Remote Sensing Visual Grounding

OptiSAR-Net++ introduces a new cross‑domain remote sensing visual grounding task (CD‑RSVG) and the first large‑scale benchmark dataset, OptSAR‑RSVG. The framework replaces Transformer decoding with a CLIP‑based contrastive approach, employing a patch‑level Low‑Rank Adaptation Mixture of Experts for efficient cross‑domain feature decoupling and a text‑guided dual‑gate fusion module for improved semantic‑visual alignment. Experiments show state‑of‑the‑art performance on OptSAR‑RSVG and DIOR‑RSVG, with notable gains in localization accuracy and computational efficiency.

By Xiaoyu Tang, Jun Dong, Jintao Cheng, Rui Fan
llmsmultimodalbenchmarkssafety
More like this →
arXiv Computer Vision
3d ago

End-to-End Self-Supervised RGB-T Tracking without Modality Misleading

ESMTrack is a fully end‑to‑end self‑supervised RGB‑T tracking framework that eliminates the need for costly modality‑aligned bounding boxes or offline pseudo‑label generation. It learns discriminative, temporally consistent representations using a grounding triplet loss on the initial annotated frame and a cross‑frame temporal triplet loss on unlabeled search frames, with reliable samples selected via forward‑backward consistency. A three‑branch architecture (fusion, RGB, thermal) and a modality decoupling mechanism mitigate modality dominance bias, enabling competitive state‑of‑the‑art performance, strong cross‑dataset generalization, and real‑time inference on five RGB‑T benchmarks.

By Shenglan Li, Rui Yao, Kunyang Sun, Hong Jia, Yong Zhou, Javen Qinfeng Shi, Xinyu Zhang
efficiencymultimodalbenchmarkssafety
More like this →