Learning generalizable representation and classifier for class-imbalanced data is challenging for data-driven deep models.
In this paper, to better handle the tradeoff problem, we propose Diversity-Measurable Anomaly Detection (DMAD) framework to enhance reconstruction diversity while avoid the undesired generalization on anomalies.
Ranked #1 on Anomaly Detection on UCSD Ped2
In this paper, we propose a Clothes-based Adversarial Loss (CAL) to mine clothes-irrelevant features from the original RGB images by penalizing the predictive power of re-id model w. r. t.
Ranked #2 on Person Re-Identification on PRCC
The current popular two-stream, two-stage tracking framework extracts the template and the search region features separately and then performs relation modeling, thus the extracted features lack the awareness of the target and have limited target-background discriminability.
Ranked #3 on Visual Object Tracking on UAV123
To further improve SBM, an Integration-and-Distribution Module (IDM) is introduced to enhance frame-level representations.
Our method significantly outperforms existing methods on the occlusion datasets, while remains top even superior performance on holistic datasets.
Detail Branch processes frames at original resolution to preserve the detailed visual clues, and Context Branch with a down-sampling strategy is employed to capture long-range contexts.
This paper proposes a novel model, named Continuity-Discrimination Convolutional Neural Network (CD-CNN), for visual object tracking.
Furthermore, a Channel IAU (CIAU) module is designed to model the semantic contextual interactions between channel features to enhance the feature representation, especially for small-scale visual cues and body parts.
This paper proposes a Temporal Complementary Learning Network that extracts complementary features of consecutive video frames for video person re-identification.
Due to the imperfect person detection results and posture changes, temporal appearance misalignment is unavoidable in video-based person re-identification (ReID).
For example, the fixed label assignment strategy and regression loss function cannot fit the distribution change of proposals and thus are harmful to training high quality detectors.
Ranked #89 on Object Detection on COCO test-dev
With back propagation, temporal knowledge can be transferred to enhance the image features and the information asymmetry problem can be alleviated.
Ranked #8 on Person Re-Identification on iLIDS-VID
For one thing, the spatial structure of a pedestrian frame can be used to predict the occluded body parts from the unoccluded body parts of this frame.
Person re-identification (reID) benefits greatly from deep convolutional neural networks (CNNs) which learn robust feature embeddings.
Recent researches attempt to improve the detection performance by adopting the idea of cascade for single-stage detectors.
no code implementations • 19 Feb 2019 • Chen Change Loy, Dahua Lin, Wanli Ouyang, Yuanjun Xiong, Shuo Yang, Qingqiu Huang, Dongzhan Zhou, Wei Xia, Quanquan Li, Ping Luo, Junjie Yan, Jian-Feng Wang, Zuoxin Li, Ye Yuan, Boxun Li, Shuai Shao, Gang Yu, Fangyun Wei, Xiang Ming, Dong Chen, Shifeng Zhang, Cheng Chi, Zhen Lei, Stan Z. Li, Hongkai Zhang, Bingpeng Ma, Hong Chang, Shiguang Shan, Xilin Chen, Wu Liu, Boyan Zhou, Huaxiong Li, Peng Cheng, Tao Mei, Artem Kukharenko, Artem Vasenin, Nikolay Sergievskiy, Hua Yang, Liangqi Li, Qiling Xu, Yuan Hong, Lin Chen, Mingjun Sun, Yirong Mao, Shiying Luo, Yongjun Li, Ruiping Wang, Qiaokang Xie, Ziyang Wu, Lei Lu, Yiheng Liu, Wengang Zhou
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
In this paper, we propose a novel framework, called Deep Structural Ranking, for visual relationship detection.
In this paper, based on M-estimation from robust statistics, we develop a robust path-based spectral clustering method by defining a robust path-based similarity measure for spectral clustering under both unsupervised and semi-supervised settings.
In this work, we revisit the more traditional interpolation-based methods, that were popular before, now with the help of deep learning.
In this paper, we propose a generalized Unsupervised Manifold Alignment (GUMA) method to build the connections between different but correlated datasets without any known correspondences.
Identifying subjects with variations caused by poses is one of the most challenging tasks in face recognition, since the difference in appearances caused by poses may be even larger than the difference due to identity.
In this paper, we propose a simple but effective coupled neural network, called Deeply Coupled Autoencoder Networks (DCAN), which seeks to build two deep neural networks, coupled with each other in every corresponding layers.