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
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works36 from public data
- Future Frame Prediction for Anomaly Detection - A New Baseline1,526
This paper proposes to tackle the anomaly detection problem within a video prediction framework by introducing a motion (temporal) constraint in video prediction by enforcing the optical flow between predicted frames and ground truth frames to be consistent, and is the first work that introduces a temporal constraint into the video prediction task.
- 243
- 219
- Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding135
This work mimics the human behavior of ‘Look Before You Leap’ to design an LBYL-Net, which takes full consideration of contextual information, and outperforms all state-of-the-art two-stage and one-stage methods on ReferitGame.
- TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration127
The approach can generate realistic and coherent dance movements conditioned on both text and music while maintaining comparable performance with the two single modalities, and two novel metrics are introduced to measure the coherence and freezing percentage of the generated motion.
- 127
- Single-Image Piece-Wise Planar 3D Reconstruction via Associative Embedding111
A novel two-stage method based on associative embedding, inspired by its recent success in instance segmentation, that is able to detect an arbitrary number of planes and facilitate many real-time applications such as visual SLAM and human-robot interaction.
- Believe It or Not, We Know What You Are Looking At!105
This work builds a video gaze following dataset, where the ground truth is annotated by the observers in the videos, and significantly outperforms existing methods, which validates the effectiveness of the two-stage solution based gaze following.
- Towards Fast Adaptation of Neural Architectures with Meta Learning96
A novel Transferable Neural Architecture Search method based on meta-learning, which learns a meta-architecture that is able to adapt to a new task quickly through a few gradient steps, which makes the transferred architecture suitable for the specific task.
- Priority-Centric Human Motion Generation in Discrete Latent Space93
A Priority-Centric Motion Discrete Diffusion Model (M2DM) is introduced, which utilizes a Transformer-based VQ-VAE to derive a concise, discrete motion representation, incorporating a global self-attention mechanism and a regularization term to counteract code collapse.
- 85
- 81
- TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting80
This work introduces a new large-scale repetitive action counting dataset covering a wide variety of video lengths, along with more realistic situations where action interruption or action inconsistencies occur in the video, and proposes a density map regression-based method to predict the action period.
- Dataset Quantization69
DQ is the first method that can successfully distill large-scale datasets such as ImageNet-1k with a state-of-the-art compression ratio and can be trained with negligible or no performance drop for both vision tasks as well as language tasks.
- 49
- RGBD Based Gaze Estimation via Multi-Task CNN38
This paper proposes a CNN-based multi-task learning framework to simultaneously refine depth images and predict gaze points to decompose gaze point estimation into eyeball pose, head pose, and 3D eye position estimation.
- 34
- 32
- Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane32
An information plane based framework is designed to evaluate the capability of DNNs for image classification tasks and shows the information plane is more informative than loss curve and applies mutual information to infer the model’s capability for recognizing objects of each class.
- Utilizing Information Bottleneck to Evaluate the Capability of Deep Neural Networks for Image Classification27
An information plane-based framework to evaluate the capability of DNNs (including CNNs) for image classification and explains the efficiency of transfer learning in the deep learning area.
- SVIP: Sequence VerIfication for Procedures in Videos24
A simple but effective baseline based on the transformer encoder with a novel sequence alignment loss is introduced to better characterize long-term dependency between steps, which outperforms other action recognition methods.
- Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos21
Extensive experiments on video sequence verification and text-to-video matching show that the weakly supervised sequential video understanding method outperforms baselines by a large margin, which validates the effectiveness of the proposed approach.
- 20
- 16
- RGB-D-based gaze point estimation via multi-column CNNs and facial landmarks global optimization12
This work utilizes a multi-column CNNs framework to estimate the gaze point of a person sitting in front of a display from an RGB-D image of the person, and outperforms existing methods by a large margin on both the dataset and the Eyediap dataset.
Publication data from OpenAlex; 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.