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
- Deng-Ping FanSuggested from co-authorship
- Rynson W. H. LauSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works29 from public data
- Camouflaged Object Segmentation with Distraction Mining564
This paper develops a bio-inspired framework, termed Positioning and Focus Network (PFNet), which mimics the process of predation in nature and significantly outperforms 18 cutting-edge models on three challenging datasets under four standard metrics.
- 160
- DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution With Large Factors120
This paper proposes a deep recurrent fusion network (DRFN), which utilizes transposed convolution instead of bicubic interpolation for upsampling and integrates different-level features extracted from recurrent residual blocks to reconstruct the final HR images.
- 116
- Where Is My Mirror?107
This work presents a novel method to segment mirrors from an input image, and proposes a novel network, called MirrorNet, for mirror segmentation, by modeling both semantical and low-level color/texture discontinuities between the contents inside and outside of the mirrors.
- 94
- 88
- A Two-Stage Attentive Network for Single Image Super-Resolution85
This paper designs a novel multi-context attentive block (MCAB) to make the network focus on more informative contextual features and presents an essential refined attention block (RAB) which could explore useful cues in HR space for reconstructing fine-detailed HR image.
- 31
- Large-Field Contextual Feature Learning for Glass Detection30
A novel glass detection network, called GDNet-B, is proposed, which explores abundant contextual cues in a large field-of-view via a novel large-field contextual feature integration (LCFI) module and integrates both high-level and low-level boundary features with a boundary feature enhancement (BFE) module.
- Camouflaged Object Segmentation with Omni Perception29
An omni perception network (OPNet) with two novel modules, i.e. the pyramid positioning module (PPM) and dual focus module (DFM) are proposed to integrate local features and global representations for accurate positioning of the camouflaged objects and focus on their boundaries, respectively.
- 27
- 19
- Deep Polarization Reconstruction with PDAVIS Events15
E2P extracts rich polarization patterns from input polarization events and enhances features through cross-modality context integration and shows that E2P produces more accurate measurement of polarization than the PDAVIS frames in challenging fast and high dynamic range scenes.
- SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost14
SAM-I2V is introduced, an effective image-to-video upgradation method for cultivating a promptable video segmentation (PVS) model and presents a resource-efficient pathway to PVS, lowering barriers for further research in PVS model design and enabling broader applications and advancements in the field.
- Event-Enhanced Multi-Modal Spiking Neural Network for Dynamic Obstacle Avoidance14
An DRL-based event-enhanced multimodal spiking actor network (EEM-SAN) that extracts information from motion events data via unsupervised representation learning and fuses Laser and event camera data with learnable thresholding is developed.
- Mirror Segmentation via Semantic-aware Contextual Contrasted Feature Learning14
This work proposes a novel network, called MirrorNet+, for mirror segmentation, by modeling both contextual contrasts and semantic associations and shows that it outperforms the related state-of-the-art detection and segmentation methods.
- 12
- Apprenticeship-Inspired Elegance: Synergistic Knowledge Distillation Empowers Spiking Neural Networks for Efficient Single-Eye Emotion Recognition11
This work introduces a novel multimodality synergistic knowledge distillation scheme that allows a lightweight, unimodal student spiking neural network (SNN) to extract rich knowledge from an event-frame multimodal teacher network, eliminating the need for specialized sensing devices.
- Skip \n: A Simple Method to Reduce Hallucination in Large Vision-Language Models11
A new perspective is proposed, suggesting that the inherent biases in LVLMs might be a key factor in hallucinations, and a simple method is proposed to effectively mitigate the hallucination of LVLMs by skipping the output of '\n'.
- RobotSeg: A Model and Dataset for Segmenting Robots in Image and Video3
RobotSeg is built upon the versatile SAM 2 foundation model but addresses its three limitations for robot segmentation, namely the lack of adaptation to articulated robots, reliance on manual prompts, and the need for per-frame training mask annotations by introducing a structure-enhanced memory associator, a robot prompt generator, and a label-efficient training strategy.
- 2
- Can I Trust You? Advancing GUI Task Automation with Action Trust Score2
This work introduces TrustScorer, which evaluates the trustworthiness of actions generated by AI agents, enabling a new human-AI collaboration paradigm in GUI task automation, i.e., actions with low predicted trust scores are redirected for human intervention, thereby mingling human precision with AI efficiency.
- 1
- 1
- Generating Adversarial Patterns in Facial Recognition with Visual Camouflage1
An adversarial pattern generation method for face recognition and achieve universal black-box attacks by pasting the pattern on the frame of goggles by using a generative adversarial network (GAN).
- 1
- –
- –
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 2026-10-11. 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.