Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Zhigang LuoSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works199 from public data
- Learning to Purification for Unsupervised Person Re-Identification100
This work proposes to take advantage of the knowledge of teacher model in an offline scheme to purify the label noise, and achieves a state-of-the-art accuracy 85.8% @mAP and 94.5% @Rank-1 on the challenging Market-1501 benchmark with ResNet-50 under the fully unsupervised setting.
- The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report91
This paper provides a comprehensive review of the NTIRE 2024 challenge, focusing on efficient single-image super-resolution (ESR) solutions and their outcomes, and gauge the state-of-the-art in efficient single-image super-resolution.
- 86
- 71
- Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models62
A first-of-its-kind computational analysis of VQA datasets via designing minimalistic BVQA models that cast doubt on the current progress in BVQA, and shed light on good practices of constructing next-generation VQA datasets and models.
- Semi-online Multi-people Tracking by Re-identification60
This paper proposes a novel semi-online approach to tracking multiple people in a frame-by-frame manner by exploring the time, space and multi-camera relationship of detection hypotheses in the near future frames, and is the first semi-online approach achieved by re-identification.
- MambaTrack: A Simple Baseline for Multiple Object Tracking with State Space Model58
This work introduces a Mamba-based motion model named Mamba moTion Predictor (MTP), designed to model the complex motion patterns of objects like dancers and athletes, and employs it in an autoregressive way to compensate for missing observations by utilizing its own predictions as inputs, thereby contributing to more consistent trajectories.
- 58
- Bilateral Dependency Optimization54
Experiments show that BiDO achieves the state-of-the-art defense performance for a variety of datasets, classifiers, and MI attacks while suffering a minor classification-accuracy drop compared to the well-trained classifier with no defense, which lights up a novel road to defend against MI attacks.
- 49
- Maximum Mean and Covariance Discrepancy for Unsupervised Domain Adaptation49
An unsupervised learning model based on MMCD abbreviated as McDA was proposed and efficiently optimized to resolve the domain adaptation problem, and experiments on image classification show that McDA outperforms other representative domain adaptation methods, which implies the effectiveness of MMCD in domain adaptation.
- 1 st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results48
A new benchmark is introduced, called SeaDronesSee Object Detection v2, which extends the previous benchmark by including more classes and footage and is summarized in the report.
- 41
- 37
- Deep Entity Linking via Eliminating Semantic Ambiguity With BERT35
This paper introduces the advanced language representation model called BERT (Bidirectional Encoder Representations from Transformers) and designs a hard negative samples mining strategy to fine-tune it accordingly, and is the first to equip entity linking task with the powerful pre-trained general language model by deliberately tackling its potential shortcoming of learning literally.
- Towards Efficient Partially Relevant Video Retrieval With Active Moment Discovering31
This work is committed to discovering video moments that are semantically consistent with their queries and introduces a moment diversity loss to encourage different moments of distinct regions and a moment relevance loss to promote semantically query-relevant moments, which cooperate with a partially relevant retrieval loss for end-to-end optimization.
- 30
- 30
- 27
- Tackling Noisy Labels With Network Parameter Additive Decomposition26
To decouple the memorization of clean data and mislabeled data, and further reduce the side effect of mislabeled data, additive decomposition on network parameters is performed.
- 26
- 24
- 23
- 23
- 22
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.