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
- Farid BoussaïdSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works86 from public data
- Human Action Recognition From Various Data Modalities: A Review848
This article presents a comprehensive survey of recent progress in deep learning methods for HAR based on the type of input data modality, including the fusion-based and the co-learning-based frameworks.
- 270
- DiffPose: Toward More Reliable 3D Pose Estimation194
This work explores a novel pose estimation framework (DiffPose) that formulates 3D pose estimation as a reverse diffusion process and significantly outperforms existing methods on the widely used pose estimation benchmarks Human3.6M and MPI-INF-3DHP.
- 172
- 126
- Hierarchical Paired Channel Fusion Network for Street Scene Change Detection97
A novel Hierarchical Paired Channel Fusion Network (HPCFNet) is presented, which utilizes the adaptive fusion of paired feature channels to adapt to the scale and location diversities of the scene change regions.
- Computer Vision for Human–Machine Interaction87
This chapter focuses on the gesture recognition task for HMI and introduces current deep learning methods that have been used for human motion analysis and RGB-D-based gesture recognition and briefly introduces the convolutional neural networks.
- A survey of automated data augmentation algorithms for deep learning-based image classification tasks86
The underlying reasons of the emergence of AutoDA technology from the perspective of image classification are discussed, and three key components of a standard AutoDA model are identified: a search space, a search algorithm and an evaluation function.
- 73
- 58
- Long-Term Anticipation of Activities with Cycle Consistency58
A framework for anticipating future activities directly from the features of the observed frames and train it in an end-to-end fashion is proposed and achieves state-of-the-art results on two datasets: the Breakfast dataset and 50Salads.
- Progressive Video Summarization via Multimodal Self-supervised Learning57
A multimodal self-supervised learning framework to obtain semantic representations of videos, which benefits the video summarization task and introduces a progressive video summary method, where the important content in a video is pinpointed progressively to generate better summaries.
- Video Joint Modelling Based on Hierarchical Transformer for Co-summarization55
Video Joint Modelling based on Hierarchical Transformer is proposed for co-summarization, which takes into consideration the semantic dependencies across videos, and Transformer-based video representation reconstruction is introduced to maximize the high-level similarity between the summary and the original video.
- Spatial-Temporal Transformer for 3D Point Cloud Sequences51
This paper proposes a novel frame-work named Point Spatial-Temporal Transformer (PST2) to learn spatial-temporal representations from dynamic 3D point cloud sequences and shows that the PST2 outperforms existing methods on all datasets.
- 50
- 50
- Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports48
This paper introduces the first dataset, named Sports-QA, specifically designed for the sports VideoQA task, and proposes a new Auto-Focus Transformer (AFT) capable of automatically focusing on particular scales of temporal information for question answering.
- Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation46
This work forms cross-domain image translation as a denoising diffusion process and utilizes a novel Semantic Gradient Guidance (SGG) method to constrain the translation process, conditioning it on the pixel-wise source labels.
- Human Interaction Prediction Using Deep Temporal Features46
The proposed method to use flow coding images to represent the low-level motion information in videos and extract deep temporal features using a deep convolutional neural network architecture outperforms the state of the art methods for human interaction prediction.
- 44
- Unsupervised Domain Adaptation via Domain-Adaptive Diffusion41
This work proposes a novel Domain-Adaptive Diffusion (DAD) module accompanied by a Mutual Learning Strategy (MLS), which can gradually convert data distribution from the source domain to the target domain while enabling the classification model to learn along the domain transition process.
- Part-Aware Unified Representation of Language and Skeleton for Zero-Shot Action Recognition40
It is argued that relying solely on aligning label-level se-mantics and global skeleton features is insufficient to effectively transfer locally consistent visual knowledge from seen to unseen classes, and Part-aware Unified Representation between Language and Skeleton (PURLS) is introduced to explore visual-semantic alignment at both local and global scales.
- Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition34
The Adaptive Local-Component-aware Graph Convolutional Network is presented, which replaces the comparison metric with a focused sum of similarity measurements on aligned local embedding of action-critical spatial/temporal segments and helps the model reach state-of-the-art status.
- 32
- 28
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.