Yihong Gong

Yihong Gong

Auto-generated profile, based on publicly available information

Yihong Gong

Xi'an Jiaotong University, Xi'an, China

Research Focus & Metrics

Academic Career Length

31Years (1996-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 October 2018
Verified
Book Chapter
Closed access
PDF file
WSWeiwei Shi
Weiwei Shi
YGYihong Gong
Yihong Gong
CDChris Ding
Chris Ding
ZMZhiheng Ma
Zhiheng Ma
XTXiaoyu Tao
Xiaoyu Tao
NZNanning Zheng
Nanning Zheng

19 March 2020 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
YHYuhang He
Yuhang He
XWXing Wei
Xing Wei
XHXiaopeng Hong
Xiaopeng Hong
WSWeiwei Shi
Weiwei Shi
YGYihong Gong
Yihong Gong
This paper focuses on the Multi-Target Multi-Camera Tracking task (MTMCT), which aims at tracking multiple targets within a multi-camera network. As the trajectory of each target is inherently split into multiple sub-trajectories (namely local tracklets) in a multi-camera network, a major challenge of MTMCT is how to accurately match the local tracklets generated within each camera across different cameras and generate a complete global trajectory for each target, i.e., the cross-camera tracklet matching problem. We solve the cross-camera tracklet matching problem by TRACklet-to-Target Assignment (TRACTA), and propose the Restricted Non-negative Matrix Factorization (RNMF) algorithm to compute the optimal assignment solution that meets a set of constraints, which should be in force in practice. TRACTA can correct the tracking errors caused by occlusions and missed detections in local tracklets, and produce a complete global trajectory for each target across all the cameras. Moreover, we also develop an analytical way of estimating the total number of targets in the camera network, which plays an important role to compute the tracklet-to-target assignment. Experimental evaluations and ablation studies on four MTMCT benchmark datasets show the superiority of the proposed TRACTA method.

13 November 2020
Verified
Book Chapter
Closed access
PDF file
XTXiaoyu Tao
Xiaoyu Tao
XCXinyuan Chang
Xinyuan Chang
XHXiaopeng Hong
Xiaopeng Hong
XWXing Wei
Xing Wei
YGYihong Gong
Yihong Gong

16 June 2024
Verified
Conference Paper
Closed access
YBYifan Bai
Yifan Bai
ZZZeyang Zhao
Zeyang Zhao
YGYihong Gong
Yihong Gong
XWXing Wei
Xing Wei
We present ARTrackV2, which integrates two pivotal aspects of tracking: determining where to look (localization) and how to describe (appearance analysis) the target object across video frames. Building on the foundation of its predecessor, ARTrackV2 extends the concept by introducing a unified generative framework to “read out” object's trajectory and “retell” its appearance in an autoregressive manner. This approach fosters a time-continuous methodology that models the joint evolution of motion and visual features, guided by previous estimates. Furthermore, ARTrackV2 stands out for its efficiency and simplicity, obviating the less efficient intra-frame autoregression and hand-tuned parameters for appearance updates. Despite its simplicity, ARTrackV2 achieves state-of-the-art performance on prevailing benchmark datasets while demonstrating a remarkable efficiency improvement. In particular, ARTrackV2 achieves an AO score of 79. 5% on GOT-10k and an AUC of 86. 1% on TrackingNet while being 3.6× faster than ARTrack.

7 October 2018
Verified
Book Chapter
Closed access
PDF file
XWXing Wei
Xing Wei
YZYue Zhang
Yue Zhang
YGYihong Gong
Yihong Gong
JZJiawei Zhang
Jiawei Zhang
NZNanning Zheng
Nanning Zheng

4 February 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
YLYu Liu
Yu Liu
XHXiaopeng Hong
Xiaopeng Hong
XTXiaoyu Tao
Xiaoyu Tao
SDSonglin Dong
Songlin Dong
Jingang ShiJingang Shi
Jingang Shi
YGYihong Gong
Yihong Gong
Deep models have shown to be vulnerable to catastrophic forgetting, a phenomenon that the recognition performance on old data degrades when a pre-trained model is fine-tuned on new data. Knowledge distillation (KD) is a popular incremental approach to alleviate catastrophic forgetting. However, it usually fixes the absolute values of neural responses for isolated historical instances, without considering the intrinsic structure of the responses by a convolutional neural network (CNN) model. To overcome this limitation, we recognize the importance of the global property of the whole instance set and treat it as a behavior characteristic of a CNN model relevant to model incremental learning. On this basis: 1) we design an instance neighborhood-preserving (INP) loss to maintain the order of pair-wise instance similarities of the old model in the feature space; 2) we devise a label priority-preserving (LPP) loss to preserve the label ranking lists within instance-wise label probability vectors in the output space; and 3) we introduce an efficient derivable ranking algorithm for calculating the two loss functions. Extensive experiments conducted on CIFAR100 and ImageNet show that our approach achieves the state-of-the-art performance.