3 papers
cs.CV2024
P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Clouds
Jiahao Nie, Fei Xie, Sifan Zhou +3
3D single object tracking (SOT) methods based on appearance matching has long suffered from insufficient appearance information incurred by incomplete, textureless and semantically…
cs.CL2024
SentiCSE: A Sentiment-aware Contrastive Sentence Embedding Framework with Sentiment-guided Textual Similarity
Jaemin Kim, Yohan Na, Kangmin Kim +2
Recently, sentiment-aware pre-trained language models (PLMs) demonstrate impressive results in downstream sentiment analysis tasks. However, they neglect to evaluate the quality of…
cs.CV2024
Towards Category Unification of 3D Single Object Tracking on Point Clouds
Jiahao Nie, Zhiwei He, Xudong Lv +3
Category-specific models are provenly valuable methods in 3D single object tracking (SOT) regardless of Siamese or motion-centric paradigms. However, such over-specialized model de…