papers

Publications (9)

cs.CV2021

Video Temporal Relationship Mining for Data-Efficient Person Re-identification

Siyu Chen, Dengjie Li, Lishuai Gao +3

This paper is a technical report to our submission to the ICCV 2021 VIPriors Re-identification Challenge. In order to make full use of the visual inductive priors of the data, we t…

eess.IV2021

A Lossless Intra Reference Block Recompression Scheme for Bandwidth Reduction in HEVC-IBC

Jiyuan Hu, Jun Wang, Guangyu Zhong +3

The reference frame memory accesses in inter prediction result in high DRAM bandwidth requirement and power consumption. This problem is more intensive by the adoption of intra blo…

cs.PF2014

Performance Benefits of DataMPI: A Case Study with BigDataBench

Fan Liang, Chen Feng, Xiaoyi Lu +1

Apache Hadoop and Spark are gaining prominence in Big Data processing and analytics. Both of them are widely deployed on Internet companies. On the other hand, high-performance dat…

cs.CV2022

SoccerNet 2022 Challenges Results

Silvio Giancola, Anthony Cioppa, Adrien Deliège +91

The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team. In 2022, the challenges were composed of 6 vision-based tasks:…

cs.CV2023

Adaptive Sparse Pairwise Loss for Object Re-Identification

Xiao Zhou, Yujie Zhong, Zhen Cheng +2

Object re-identification (ReID) aims to find instances with the same identity as the given probe from a large gallery. Pairwise losses play an important role in training a strong R…

cs.CL2021

Learning Neural Templates for Recommender Dialogue System

Zujie Liang, Huang Hu, Can Xu +6

Though recent end-to-end neural models have shown promising progress on Conversational Recommender System (CRS), two key challenges still remain. First, the recommended items canno…