Tao Wang

Tao Wang

Auto-generated profile, based on publicly available information

Tao Wang

Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University, Nanshan, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
20 March 2024 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
TWTao Wang
Tao Wang
MLMengyuan Liu
Mengyuan Liu
HLHong Liu
Hong Liu
WLWenhao Li
Wenhao Li
MBMiaoju Ban
Miaoju Ban
YLYidi Li
Yidi Li
Occluded person re-identification is a challenging problem due to the destruction of occluders in different camera views. Most existing paradigms focus on visible human body parts through some external models to reduce noise interference. However, the feature misalignment problem caused by discarded occlusions negatively affects the performance of the network. Different from most previous works that discard the occluded regions, we present Feature Completion Transformer (FCFormer) that reduces noise interference and complements missing features in occluded parts. Specifically, Occlusion Instance Augmentation is proposed to simulate real and diverse occlusion situations on the holistic image, which enlarges the occlusion samples in the training set and forms aligned occluded-holistic pairs. To reduce the interference of noise, a two-stream architecture is proposed to learn pairwise discriminative features from aligned image pairs, while obtaining self-aligned occluded-holistic feature level sample-label pairs without additional auxiliary models. To complement the features of occluded regions, a Feature Completion Decoder is designed to aggregate possible information from self-generated occluded features in a self-supervised manner. Further, in order to correlate the completion features with identity information, Feature Completion Consistency loss is introduced to enforce the distribution of the generated completion features to be consistent with the real holistic feature distribution. In addition, we propose the Cross Hard Triplet loss to further bridge the gap between completion features and extracting features under the same ID. Extensive experiments over five challenging datasets demonstrate that the proposed FCFormer achieves superior performance and outperforms the state-of-theart methods by significant margins on Occluded-Duke dataset.

26 October 2023
Verified
Conference Paper
Open access
PGPeini Guo
Peini Guo
HLHong Liu
Hong Liu
JWJianbing Wu
Jianbing Wu
GWGuoquan Wang
Guoquan Wang
TWTao Wang
Tao Wang

26 October 2023
Verified
Conference Paper
Open access
XZXueyi Zhang
Xueyi Zhang
CZChengwei Zhang
Chengwei Zhang
TWTao Wang
Tao Wang
JTJun Tang
Jun Tang
SLSongyang Lao
Songyang Lao
HLHaizhou Li
Haizhou Li
Class incremental learning has yet to be explored in the field of lip-reading, which can circumvent data privacy issues and avoid the high training costs associated with joint training. In this paper, we introduce a benchmark for Class-Incremental Lip-Reading (CILR). To simultaneously improve the plasticity for new classes and stability for old classes in incremental learning, we propose a Slow-Fast Time Parameter Aggregation Network (TPAN) that decouples representation learning of new and old knowledge, taking into account the task characteristics of lip-reading. The TPAN comprises two dynamically evolving branches: one that uses fast gradient descent and the other employs slow momentum updates to retain old knowledge while adapting to new knowledge. Additionally, to achieve efficient knowledge transfer of the incremental model, we design a Hybrid Sequence-Distribution Distillation (HSDD) strategy to transfer knowledge in temporal feature view and classification probability view. We present a comprehensive comparison of the proposed method and previous state-of-the-art class incremental learning methods on the most commonly used lip-reading datasets LRW and LRW1000. The experimental result show that the proposed method can reduce the effect of catastrophic forgetting and improve the incremental accuracy.