Bridge then Begin Anew: Generating Target-relevant Intermediate Model for Source-free Visual Emotion Adaptationby Jiankun Zhu,…
Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learningby Di Xiong, Shuoyuan Wang, Lei Zhang,…
Hybrid CNN-LSTM based Indoor Pedestrian Localization with CSI Fingerprint Mapsby Muhammad Emad-ud-dinFirst submitted to arxiv…
Unsupervised Region-Based Image Editing of Denoising Diffusion Modelsby Zixiang Li, Yue Song, Renshuai Tao, Xiaohong…
ArtAug: Enhancing Text-to-Image Generation through Synthesis-Understanding Interactionby Zhongjie Duan, Qianyi Zhao, Cen Chen, Daoyuan Chen,…
SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detectionby Xing Liufu, Chaolei Tan, Xiaotong Lin, Yonggang…
CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Modelsby Zihui Cheng,…
Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCOby Umer Butt, Stalin Veranasi, Günter…
LMUnit: Fine-grained Evaluation with Natural Language Unit Testsby Jon Saad-Falcon, Rajan Vivek, William Berrios, Nandita…
Previous Knowledge Utilization In Online Anytime Belief Space Planningby Michael Novitsky, Moran Barenboim, Vadim IndelmanFirst…