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
- Chi–Keung TangSuggested from co-authorship
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works46 from public data
- Memory-Attended Recurrent Network for Video Captioning240
The Memory-Attended Recurrent Network (MARN) for video captioning is proposed, in which a memory structure is designed to explore the full-spectrum correspondence between a word and its various similar visual contexts across videos in training data.
- Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers239
The explicit modeling of occlusion relationship with bilayer structure naturally decouples the boundaries of both the occluding and occluded instances, and considers the interaction between them during mask regression, to validate the efficacy of bilayer decoupling on both one-stage and two-stage object detectors with different backbones and network layer choices.
- 200
- Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training Data185
A novel data augmentation method that is scalable for synthesizing massive amount of training data for training 2D-to-3D networks, can effectively reduce dataset bias and generalizes significantly better to unseen and rare poses.
- Mask Transfiner for High-Quality Instance Segmentation173
This paper presents Mask Transfiner, a transformer-based approach to instance segmentation that decomposes and represents the image regions as a quadtree, allowing it to predict highly accurate instance masks, at a low computational cost.
- Reflective Decoding Network for Image Captioning109
It is shown that vocabulary coherence between words and syntactic paradigm of sentences are also important to generate high-quality image captioning, and the proposed Reflective Decoding Network (RDN) enhances both the long-sequence dependency and position perception of words in a caption decoder.
- 102
- LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning87
This work delves into reasoning segmentation, a novel task that enables segmentation system to reason and interpret implicit user intention via large language model reasoning and then segment the corresponding target.
- OVTrack: Open-Vocabulary Multiple Object Tracking86
OVTrack is developed, an open-vocabulary tracker that is capable of tracking arbitrary object classes and its design is based on two key ingredients, leveraging vision-language models for both classification and association via knowledge distillation and a data hallucination strategy for robust appearance feature learning from denoising diffusion probabilistic models.
- Matching Anything by Segmenting Anything83
This work proposes MASA, a novel method for robust instance association learning, capable of matching any objects within videos across diverse domains without tracking labels, Leveraging the rich object segmentation from the Segment Anything Model (SAM).
- Cascade-DETR: Delving into High-Quality Universal Object Detection69
Cascade-DETR is introduced for high-quality universal object detection, and the Cascade Attention layer is proposed, which explicitly integrates object-centric information into the detection decoder by limiting the attention to the previous box prediction.
- GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-Aware Supervision56
A novel end-to-end framework named GSNet (Geometric and Scene-aware Network), which jointly estimates 6DoF poses and reconstructs detailed 3D car shapes from single urban street view, and inspires a new multi-objective loss function to regularize network training.
- Occlusion-Aware Video Object Inpainting47
Experimental results clearly demonstrate the efficacy of the occlusion-aware video object inpainting, which recovers both the complete shape and appearance for occluded objects in videos given their visible mask segmentation.
- Occlusion-Aware Instance Segmentation Via BiLayer Network Architectures37
Large and consistent improvements using one/two-stage and query-based object detectors with various backbones and network layer choices validate the generalization ability of bilayer decoupling, as shown by extensive experiments on image instance segmentation benchmarks.
- 35
- 35
- Mask-Free Video Instance Segmentation32
This work proposes MaskFreeVIS, achieving highly competitive VIS performance, while only using bounding box annotations for the object state, by introducing the Temporal KNN-patch Loss (TK-Loss), providing strong mask supervision without any labels.
- Commonality-Parsing Network Across Shape and Appearance for Partially Supervised Instance Segmentation32
This work proposes to learn the underlying class-agnostic commonalities that can be generalized from mask-annotated categories to novel categories, and significantly outperforms the state-of-the-art methods on both partially supervised setting and few-shot setting for instance segmentation on COCO dataset.
- BiMatting: Efficient Video Matting via Binarization28
BiMatting is proposed, an accurate and efficient video matting model using binarization that outperforms other binarized video matting models, including state-of-the-art (SOTA) binarization methods, by a significant margin and performs comparably to the full-precision counterpart in visual quality.
- 21
- BiVM: Accurate Binarized Neural Network for Efficient Video Matting19
The proposed BiVM surpasses alternative binarized video matting networks, including state-of-the-art (SOTA) binarization methods, by a substantial margin and achieves significant savings in computation and storage costs.
- Stable Segment Anything Model18
The first comprehensive analysis on SAM's segmentation stability across a diverse spectrum of prompt qualities is presented, revealing that given low-quality prompts, SAM's mask decoder tends to activate image features that are biased towards the background or confined to specific object parts.
- 16
- 7
- 6
- ProReflow: Progressive Reflow with Decomposed Velocity6
This paper suggests that the original training pipeline of reflow is not optimal and introduces progressive reflow, which progressively reflows the diffusion models in local timesteps until the whole diffusion progresses, reducing the difficulty of flow matching.
- 5
- 3
- AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization2
AnchorWorld is presented, a framework that advances egocentric simulation through enhanced interaction integrity and a flexible mechanism for world customization and proposes a simple yet effective mechanism for customizing self-evolving worlds.
- Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors1
GenMOJO, a novel approach that integrates rendering-based deformable 3D Gaussian optimization with generative priors for view synthesis, generates more realistic novel views of scenes and produces more accurate point tracks compared to existing approaches.
- –
- –
- –
- –
- DVPSFormer: Efficient Online Depth-aware Video Panoptic Segmentation for Autonomous Driving–
DVPSFormer is proposed, a unified online architecture designed for efficient 4D scene understanding that establishes a new state-of-the-art on the Cityscapes-DVPS and SemKITTI-DVPS benchmarks, offering a streamlined solution for online robotic perception.
- –
- –
- –
- –
- –
- –
- –
- Zero-P-to-3: Zero-Shot Partial-View Images to 3D Object–
This work proposes a novel training-free approach that integrates the local dense observations and multi-source priors for reconstruction, and introduces a fusion-based strategy to effectively align these priors in DDIM sampling, thereby generating multi-view consistent images to supervise invisible views.
- –
- –
- Image and video instance segmentation : towards better quality, robustness and annotation-efficiency–
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. 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.