Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks130 from public data
- 1,146
- 522
- Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications289
This work analyzes and discusses the benefits and limitations of SAM, while also presenting an outlook on its future development in segmentation tasks, to give a comprehensive understanding of SAM’s practical applications.
- 278
- Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition222
This is the first attempt at successfully implementing the Chain-of-Thought technique for achieving human-level video reasoning, where it shows great potential in extending it to a wider range of video understanding scenarios.
- 203
- Accurate RGB-D Salient Object Detection via Collaborative Learning190
A novel collaborative learning framework where edge, depth and saliency are leveraged in a more efficient way, which solves those problems tactfully and makes the model more lightweight, faster and more versatile.
- Video as Conditional Graph Hierarchy for Multi-Granular Question Answering154
This work proposes to model video as a conditional graph hierarchy which weaves together visual facts of different granularity in a level-wise manner, with the guidance of corresponding textual cues to align with the multi-granular essence of linguistic concepts in language queries.
- 153
- 132
- Fine-Grained Scene Graph Generation with Data Transfer127
This work proposes a novel Internal and External Data Transfer (IETrans) method, which can be applied in a plug-and-play fashion and expanded to large SGG with 1,807 predicate classes, which tries to relieve the data distribution problem by automatically creating an enhanced dataset that provides more sufficient and coherent annotations for all predicates.
- 120
- VPGTrans: Transfer Visual Prompt Generator across LLMs118
This work investigates the VPG transferability across LLMs, and develops a two-stage transfer framework named VPGTrans, which is simple yet highly effective and demonstrated to significantly speed up the transfer learning process without compromising performance.
- 118
- Memory-oriented Decoder for Light Field Salient Object Detection108
A deep-learning-based method where a novel memory-oriented decoder is tailored for light field saliency detection and deeply explore and comprehensively exploit internal correlation of focal slices for accurate prediction by designing feature fusion and integration mechanisms.
- Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization94
A unified learning approach to simultaneously modeling the coarse- and fine-grained retrieval by considering the multi-grained uncertainty is introduced, which prevents the model from pushing away potential candidates in the early stage, and thus improves the recall rate.
- 90
- 82
- 79
- Learning Frequency-Adapted Vision Foundation Model for Domain Generalized Semantic Segmentation66
A novel Frequency-Adapted (FADA) learning scheme to separately tackle the content and style information by frequency tokens throughout the learning process, which is able to stabilize the scene content and eliminate its impact to DGSS.
- 66
- Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World63
A Cross-modal prediCate boosting (CaCao) framework, where a visually-prompted language model is learned to generate diverse fine-grained predicates in a low-resource way for open-world predicate scene graph generation (Epic).
- 57
- Learning Spectral-Decomposited Tokens for Domain Generalized Semantic Segmentation56
A novel Spectral-dEcomposed Token (SET) learning framework to advance the frontier and develops an attention optimization method to bridge the gap between style-affected representation and static tokens during inference.
- Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection51
A deep unsupervised RGB-D saliency detection approach, which requires no manual pixel-level annotation during training, and can be adapted to work in fully-supervised situation.
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 2026-10-12. 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.