Search Results - "Tang, Shixiang"

Morphology selection kinetics of crystallization in a sphere by Chen, Yanshuang, Yao, Zhenwei, Tang, Shixiang, Tong, Hua, Yanagishima, Taiki, Tanaka, Hajime, Tan, Peng

“…Crystallization under geometrical confinement is of fundamental importance in condensed matter physics, biophysics and material science. Even the influence of…”
Get full text

Fast crystal growth at ultra-low temperatures by Gao, Qiong, Ai, Jingdong, Tang, Shixiang, Li, Minhuan, Chen, Yanshuang, Huang, Jiping, Tong, Hua, Xu, Lei, Xu, Limei, Tanaka, Hajime, Tan, Peng

“…It is believed that the slow liquid diffusion and geometric frustration brought by a rapid, deep quench inhibit fast crystallization and promote vitrification…”
Get full text

Achieving adjustable elasticity with non-affine to affine transition by Shen, Xiangying, Fang, Chenchao, Jin, Zhipeng, Tong, Hua, Tang, Shixiang, Shen, Hongchuan, Xu, Ning, Lo, Jack Hau Yung, Xu, Xinliang, Xu, Lei

“…For various engineering and industrial applications it is desirable to realize mechanical systems with broadly adjustable elasticity to respond flexibly to the…”
Get full text

Feature Erasing and Diffusion Network for Occluded Person Re-Identification by Wang, Zhikang, Zhu, Feng, Tang, Shixiang, Zhao, Rui, He, Lihuo, Song, Jiangning

“…Occluded person re-identification (ReID) aims at matching occluded person images to holistic ones across different camera views. Target Pedestrians (TP) are…”
Get full text

Complementary Relation Contrastive Distillation by Zhu, Jinguo, Tang, Shixiang, Chen, Dapeng, Yu, Shijie, Liu, Yakun, Rong, Mingzhe, Yang, Aijun, Wang, Xiaohua

“…Knowledge distillation aims to transfer representation ability from a teacher model to a student model. Previous approaches focus on either individual…”
Get full text

Adept: Annotation-denoising auxiliary tasks with discrete cosine transform map and keypoint for human-centric pretraining by He, Weizhen, Yan, Yunfeng, Tang, Shixiang, Deng, Yiheng, Zhong, Yangyang, Luo, Pengxin, Qi, Donglian

“…Human-centric perception is the core of diverse computer vision tasks and has been a long-standing research focus. However, previous research studied these…”
Get full text

Online Pseudo Label Generation by Hierarchical Cluster Dynamics for Adaptive Person Re-identification by Zheng, Yi, Tang, Shixiang, Teng, Guolong, Ge, Yixiao, Liu, Kaijian, Qin, Jing, Qi, Donglian, Chen, Dapeng

“…Adaptive person re-identification (adaptive ReID) targets at transferring learned knowledge from the labeled source domain to the unlabeled target domain…”
Get full text

Layerwise Optimization by Gradient Decomposition for Continual Learning by Tang, Shixiang, Chen, Dapeng, Zhu, Jinguo, Yu, Shijie, Ouyang, Wanli

“…Deep neural networks achieve state-of-the-art and sometimes super-human performance across various domains. However, when learning tasks sequentially, the…”
Get full text

Relation-Aware Distribution Representation Network for Person Clustering With Multiple Modalities by Liu, Kaijian, Tang, Shixiang, Li, Ziyue, Li, Zhishuai, Bai, Lei, Zhu, Feng, Zhao, Rui

“…Person clustering with multi-modal clues, including faces, bodies, and voices, is critical for various tasks, such as movie parsing and identity-based movie…”
Get full text

Revisiting the Transferability of Supervised Pretraining: an MLP Perspective by Wang, Yizhou, Tang, Shixiang, Zhu, Feng, Bai, Lei, Zhao, Rui, Qi, Donglian, Ouyang, Wanli

“…The pretrain-finetune paradigm is a classical pipeline in visual learning. Recent progress on unsupervised pretraining methods shows superior transfer…”
Get full text

Mutual CRF-GNN for Few-shot Learning by Tang, Shixiang, Chen, Dapeng, Bai, Lei, Liu, Kaijian, Ge, Yixiao, Ouyang, Wanli

“…Graph-neural-networks (GNN) is a rising trend for fewshot learning. A critical component in GNN is the affinity. Typically, affinity in GNN is mainly computed…”
Get full text

Firms’ value impact of C2M mode empowered by big data based on event study by Li, Bo, Xing, Ruxiao, Guo, Wenya, Tang, Shixiang

“…Purpose This study aims to analyze and discuss whether and how consumer-to-manufacturer (C2M) mode empowered by e-commerce retail platforms’ big data affects…”
Get full text

Continual Representation Learning for Biometric Identification by Zhao, Bo, Tang, Shixiang, Chen, Dapeng, Bilen, Hakan, Zhao, Rui

“…With the explosion of digital data in recent years, continuously learning new tasks from a stream of data without forgetting previously acquired knowledge has…”
Get full text

Trust Your Partner's Friends: Hierarchical Cross-Modal Contrastive Pre-Training for Video-Text Retrieval by Xiang, Yuhan, Liu, Kaijian, Tang, Shixiang, Bai, Lei, Zhu, Feng, Zhao, Rui, Lin, Xianming

“…Video-text retrieval has greatly benefited from the massive web video in recent years, while the performance is still limited to the weak supervision from the…”
Get full text

UniHCP: A Unified Model for Human-Centric Perceptions by Ci, Yuanzheng, Wang, Yizhou, Chen, Meilin, Tang, Shixiang, Bai, Lei, Zhu, Feng, Zhao, Rui, Yu, Fengwei, Qi, Donglian, Ouyang, Wanli

“…Human-centric perceptions (e.g., pose estimation, human parsing, pedestrian detection, person re-identification, etc.) play a key role in industrial…”
Get full text

HumanBench: Towards General Human-Centric Perception with Projector Assisted Pretraining by Tang, Shixiang, Chen, Cheng, Xie, Qingsong, Chen, Meilin, Wang, Yizhou, Ci, Yuanzheng, Bai, Lei, Zhu, Feng, Yang, Haiyang, Yi, Li, Zhao, Rui, Ouyang, Wanli

“…Human-centric perceptions include a variety of vision tasks, which have widespread industrial applications, including surveillance, autonomous driving, and the…”
Get full text

Two Heads Are Better Than One: A Multi-Agent System Has the Potential to Improve Scientific Idea Generation by Su, Haoyang, Chen, Renqi, Tang, Shixiang, Zheng, Xinzhe, Li, Jingzhe, Yin, Zhenfei, Ouyang, Wanli, Dong, Nanqing

“…The rapid advancement of scientific progress requires innovative tools that can accelerate discovery. While recent AI methods, particularly large language…”
Get full text

DiffFluid: Plain Diffusion Models are Effective Predictors of Flow Dynamics by Luo, Dongyu, Wu, Jianyu, Wang, Jing, Xie, Hairun, Yue, Xiangyu, Tang, Shixiang

“…We showcase the plain diffusion models with Transformers are effective predictors of fluid dynamics under various working conditions, e.g., Darcy flow and high…”
Get full text

LEAD: Exploring Logit Space Evolution for Model Selection by Hu, Zixuan, Li, Xiaotong, Tang, Shixiang, Liu, Jun, Hu, Yichun, Duan, Ling-Yu

“…The remarkable success of "pretrain-then-finetune" paradigm has led to a proliferation of available pre-trained models for vision tasks. This surge presents a…”
Get full text

DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM by Wu, Yixuan, Wang, Yizhou, Tang, Shixiang, Wu, Wenhao, He, Tong, Ouyang, Wanli, Torr, Philip, Wu, Jian

“…We present DetToolChain, a novel prompting paradigm, to unleash the zero-shot object detection ability of multimodal large language models (MLLMs), such as…”
Get full text