Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks25 from public data
- Hybrid Task Cascade for Instance Segmentation1,565
This work proposes a new framework, Hybrid Task Cascade (HTC), which differs in two important aspects: (1) instead of performing cascaded refinement on these two tasks separately, it interweaves them for a joint multi-stage processing; (2) it adopts a fully convolutional branch to provide spatial context, which can help distinguishing hard foreground from cluttered background.
- Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion878
- 668
- Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition343
A novel compact motion representation for video action recognition, named Optical Flow guided Feature (OFF), which enables the network to distill temporal information through a fast and robust approach and is complementary to other motion modalities such as optical flow.
- Robust Multi-Modality Multi-Object Tracking236
This study designs a generic sensor-agnostic multi-modality MOT framework (mmMOT), where each modality is capable of performing its role independently to preserve reliability, and could further improving its accuracy through a novel multi- modality fusion module.
- Vision Transformer with Progressive Sampling122
An iterative and progressive sampling strategy to locate discriminative regions and when combined with the Vision Transformer, the obtained PS-ViT network can adaptively learn where to look.
- RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model116
AG-Driver is presented, a novel retrieval-augmented multi-modal large language model that leverages in-context learning for high-performance, explainable, and generalisable autonomous driving and exhibits exceptional zero-shot generalisation capabilities to unseen environments without further training endeavours.
- Co-hierarchical analysis of shape structures97
An unsupervised co-hierarchical analysis of a set of shapes, aimed at discovering their hierarchical part structures and revealing relations between geometrically dissimilar yet functionally equivalent shape parts across the set, is introduced.
- CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor96
A novel recurrent framework that progressively filters out irrelevant texts and enhances mask quality without training efforts is introduced, which outperforms not only the training-free counter-parts, but also those fine-tuned with millions of data sam-ples, and sets the new state-of-the-art records for both zero-shot semantic and referring segmentation.
- 80
- Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability53
This work investigates an alternative strategy for pre-training, namely Knowledge Distillation as Efficient Pre-training (KDEP), aiming to efficiently transfer the learned feature representation from existing pre-trained models to new student models for future downstream tasks.
- 47
- Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation35
Inspired by object-centric learning which learns compact and robust object representations, this paper presents Slot- VPS, the first end-to-end framework for this task, which encode all panoptic entities in a video, including both foreground instances and background semantics, with a unified representation calledpanoptic slots.
- OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?20
This paper presents OxfordTVG-HIC (Humorous Image Captions), a large-scale dataset for humour generation and understanding and identifies the visual and linguistic cues influential for evoking humour prediction and generation and observes qualitatively that these cues are aligned with the benign violation theory of humour in cognitive psychology.
- 16
- Diffusion Models Need Visual Priors for Image Generation13
This work proposes Diffusion on Diffusion (DoD), an innovative multi-stage generation framework that first extracts visual priors from previously generated samples, then provides rich guidance for the diffusion model leveraging visual priors from the early stages of diffusion sampling.
- 12
- 6
- 5
- 2
- 1
- 1
- 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 2026-10-16. 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.