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
- Zhengyou ZhangSuggested from co-authorship
- Ming–Ting SunSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works240 from public data
- ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression1,895
ThiNet is proposed, an efficient and unified framework to simultaneously accelerate and compress CNN models in both training and inference stages, and it is revealed that it needs to prune filters based on statistics information computed from its next layer, not the current layer, which differentiates ThiNet from existing methods.
- The Visual Object Tracking VOT2014 Challenge Results588
The Visual Object Tracking challenge 2014, VOT2014, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance and introduces a new dataset with full annotation of targets by rotated bounding boxes and per-frame attribute.
- 340
- PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments314
A novel loss, Pixels-IoU (PIoU) Loss, is formulated to exploit both the angle and IoU for accurate OBB regression and can dramatically improve the performance of OBB detectors, particularly on objects with high aspect ratios and complex backgrounds.
- 264
- 262
- Enriched Long-Term Recurrent Convolutional Network for Facial Micro-Expression Recognition230
An Enriched Long-term Recurrent Convolutional Network (ELRCN) that first encodes each micro- expression frame into a feature vector through CNN module(s), then predicts the micro-expression by passing the feature vectorthrough a Long Short-term Memory (LSTM) module.
- A Short Survey of Recent Advances in Graph Matching223
The aim is to provide a systematic and compact framework regarding the recent development and the current state-of-the-arts in graph matching.
- Multiple Sound Sources Localization from Coarse to Fine192
A two-stage audiovisual learning framework that disentangles audio and visual representations of different categories from complex scenes, then performs cross-modal feature alignment in a coarse-to-fine manner achieves state-of-the-art results on public dataset of localization, as well as considerable performance on multi-source sound localization in complex scenes.
- Person Re-Identification with Correspondence Structure Learning175
A boosting-based approach to learn a correspondence structure which indicates the patch-wise matching probabilities between images from a target camera pair is introduced, which integrates a global matching constraint over the learned correspondence structure to exclude cross-view misalignments during the image patch matching process, hence achieving a more reliable matching score between images.
- ATRW165
A novel method for tiger re-identification is proposed, which introduces precise pose parts modeling in deep neural networks to handle large pose variation of tigers, and reaches notable performance improvement over existing re-ID methods.
- 163
- 154
- Towards Accurate One-Stage Object Detection With AP-Loss134
A novel optimization algorithm is developed, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks, and good convergence property of the proposed algorithm is verified theoretically and empirically.
- Survey on blind image forgery detection133
This survey attempts to cover the blind techniques that have been proposed for exposing forgeries, focusing on the detection techniques for three of the most common forgery types, namely copy/move, splicing and retouching.
- 132
- 129
- 126
- Deep Neural Network Compression With Single and Multiple Level Quantization125
This paper is the first to consider the network quantization from both width and depth level, and introduces incremental layer compensation to quantize layers iteratively which decreases the quantization loss in each iteration.
- Learning vision-based agile flight via differentiable physics123
An end-to-end approach that combines deep learning with first-principles physics through differentiable simulation to enable autonomous navigation by several aerial robots through complex environments at high speed is introduced.
- 109
- TA2N: Two-Stage Action Alignment Network for Few-Shot Action Recognition106
A Two-stage Action Alignment Network (TA2N) is addressed sequentially through a temporal affine transform, which warps each video feature to its action duration while dismissing the action-irrelevant feature.
- HiEve: A Large-Scale Benchmark for Human-Centric Video Analysis in Complex Events103
A new large-scale dataset with comprehensive annotations, named HiEve, for the understanding of human motions, poses, and actions in a variety of realistic events, especially in crowd and complex events, and it contains a record number of poses, the largest number of action instances, and one of the largest numbers of trajectories lasting for longer time.
- 92
- AP-Loss for Accurate One-Stage Object Detection85
A novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the Average-Precision loss (AP-loss) for the ranking problem is proposed, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks.
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.