Zobrazeno 1 - 10
of 140
pro vyhledávání: '"Li, Annan"'
Recent advancements in large language models (LLMs) have showcased impressive code generation capabilities, primarily evaluated through language-to-code benchmarks. However, these benchmarks may not fully capture a model's code understanding abilitie
Externí odkaz:
http://arxiv.org/abs/2408.10718
Gait recognition has attracted increasing attention from academia and industry as a human recognition technology from a distance in non-intrusive ways without requiring cooperation. Although advanced methods have achieved impressive success in lab sc
Externí odkaz:
http://arxiv.org/abs/2408.06834
Human gait is considered a unique biometric identifier which can be acquired in a covert manner at a distance. However, models trained on existing public domain gait datasets which are captured in controlled scenarios lead to drastic performance decl
Externí odkaz:
http://arxiv.org/abs/2201.04806
Dance challenges are going viral in video communities like TikTok nowadays. Once a challenge becomes popular, thousands of short-form videos will be uploaded in merely a couple of days. Therefore, virality prediction from dance challenges is of great
Externí odkaz:
http://arxiv.org/abs/2111.03819
Video-based person re-identification (Re-ID) which aims to associate people across non-overlapping cameras using surveillance video is a challenging task. Pedestrian attribute, such as gender, age and clothing characteristics contains rich and supple
Externí odkaz:
http://arxiv.org/abs/2108.06946
Fine-grained action recognition is attracting increasing attention due to the emerging demand of specific action understanding in real-world applications, whereas the data of rare fine-grained categories is very limited. Therefore, we propose the few
Externí odkaz:
http://arxiv.org/abs/2108.06647
Publikováno v:
ICIP 2021
Gait recognition under multiple views is an important computer vision and pattern recognition task. In the emerging convolutional neural network based approaches, the information of view angle is ignored to some extent. Instead of direct view estimat
Externí odkaz:
http://arxiv.org/abs/2108.05524
Autor:
Lu, Yaojie, Lin, Hongyu, Xu, Jin, Han, Xianpei, Tang, Jialong, Li, Annan, Sun, Le, Liao, Meng, Chen, Shaoyi
Event extraction is challenging due to the complex structure of event records and the semantic gap between text and event. Traditional methods usually extract event records by decomposing the complex structure prediction task into multiple subtasks.
Externí odkaz:
http://arxiv.org/abs/2106.09232
ISCAS participated in two subtasks of SemEval 2020 Task 5: detecting counterfactual statements and detecting antecedent and consequence. This paper describes our system which is based on pre-trained transformers. For the first subtask, we train sever
Externí odkaz:
http://arxiv.org/abs/2009.08171
Video-based person re-identification (Re-ID) is an important computer vision task. The batch-hard triplet loss frequently used in video-based person Re-ID suffers from the Distance Variance among Different Positives (DVDP) problem. In this paper, we
Externí odkaz:
http://arxiv.org/abs/2006.07597