Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks43 from public data
- Rethinking BiSeNet For Real-time Semantic Segmentation785
A novel and efficient structure named Short-Term Dense Concatenate network (STDC network) is proposed by removing structure redundancy by gradually reducing the dimension of feature maps and use the aggregation of them for image representation, which forms the basic module of STDC network.
- HCP: A Flexible CNN Framework for Multi-Label Image Classification784
Experimental results on Pascal VOC 2007 and VOC 2012 multi-label image datasets well demonstrate the superiority of the proposed HCP infrastructure over other state-of-the-arts, where an arbitrary number of object segment hypotheses are taken as the inputs.
- Cross-Domain Image Retrieval with a Dual Attribute-Aware Ranking Network431
This work proposes a Dual Attribute-aware Ranking Network (DARN) for retrieval feature learning, consisting of two sub-networks, one for each domain, whose retrieval feature representations are driven by semantic attribute learning.
- More is Less: A More Complicated Network with Less Inference Complexity302
A novel and general network structure towards accelerating the inference process of convolutional neural networks, which is more complicated in network structure yet with less inference complexity.
- 264
- 199
- 173
- 166
- 157
- Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation77
A Language-Bridged Duplex Transfer (LBDT) module is proposed which utilizes language as an intermediary bridge to accomplish explicit and adaptive spatial-temporal interaction earlier in the encoding phase.
- 64
- Scalable Diffusion Models with State Space Backbone53
This paper endeavors to train diffusion models for image data, wherein the traditional U-Net backbone is supplanted by a state space backbone, functioning on raw patches or latent space, revealing that DiS exhibits comparable, if not superior, performance to CNN-based or Transformer-based U-Net architectures of commensurate size.
- 52
- 47
- 47
- 46
- Divide and Adapt: Active Domain Adaptation via Customized Learning39
This work presents Divide-and-Adapt (DiaNA), a new ADA framework that partitions the target instances into four categories with stratified transferable properties and proposes an informativeness score that unifies the data partitioning criteria.
- EfficientRep:An Efficient Repvgg-style ConvNets with Hardware-aware Neural Network Design38
EfficientRep series convolutional networks are designed, which are high-computation hardware(e.g. GPU) friendly and applied in YOLOv6 object detection framework.
- 30
- 28
- Deep Search with Attribute-aware Deep Network22
Deep Search is presented, an attribute-aware fashion-related retrieval system, based on the convolutional neural network by taking clothes as a concrete example, and the promising retrieval results indicate the great potential of neural feature forattribute-aware retrieval task.
- 18
- Towards efficient sparse coding for scalable image annotation18
This paper develops a general and efficient framework to derive an accurate solution to the large-scale sparse coding problem through solving a series of much smaller-scale subproblems, and develops a sub-linear time complexity hashing strategy, e.g. Locality-Sensitive Hashing, which is seamlessly integrated into this framework.
- PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding16
A one-stage end-to-end Pixel-Phrase Matching Network (PPMN), which directly matches each phrase to its corresponding pixels instead of region proposals and outputs panoptic segmentation by simple combination, which achieves new state-of-the-art performance on the PNG benchmark with 4.0 absolute Average Recall gains.
- Circle & Search13
An innovative product retrieval system, called Circle & Search, enables users to naturally indicate any preferred product by simply circling the product in images as the visual query, and then returns visually and semantically similar products to the users.
- 11
- Music Consistency Models10
Music Consistency Models is presented, which leverages the concept of consistency models to efficiently synthesize mel-spectrogram for music clips, maintaining high quality while minimizing the number of sampling steps.
- 10
- Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding8
This work proposes to enrich phrases with coupled pixel and object contexts by designing a Phrase-Pixel-Object Transformer Decoder (PPO-TD), where both fine-grained part details and coarse-graining entity clues are aggregated to phrase features.
- JoyGen: Audio-Driven 3D Depth-Aware Talking-Face Video Editing7
JoyGen, a novel two-stage framework for talking-face generation, comprising audio-driven lip motion generation and visual appearance synthesis, is introduced, providing comprehensive supervision for precise lip-audio synchronization in facial generation.
- 6
- DiT: Efficient Vision Transformers with Dynamic Token Routing5
This paper proposes a data-dependent token routing strategy to elaborate the routing paths of image tokens for Dynamic Vision Transformer, dubbed DiT, which achieves superior performance and favorable complexity/accuracy trade-offs than many SoTA methods on ImageNet classification, object detection, instance segmentation, and semantic segmentation.
- 5
- Developing a visual component library for a graphical programming platform using object orientation5
The research reported in this paper makes full use of the advantages of the object-oriented methodology to develop the visual VI components for a graphical programming platform and shows how various VIs can be efficiently developed.
- RePainter: Empowering E-commerce Object Removal via Spatial-matting Reinforcement Learning4
Repainter is a reinforcement learning framework that integrates spatial-matting trajectory refinement with Group Relative Policy Optimization (GRPO) and introduces a composite reward mechanism that balances global, local, and semantic constraints, effectively reducing visual artifacts and reward hacking.
- Dual Path Network for Cross-view Geo-Localization3
This work reevaluate the square-ring partition strategy proposed in LPN and identifies a limitation in its fixed splitting strategy of features, and proposes a multi-scale ring partition strategy that effectively partitions the features at different scales to accommodate the change in the target scale.
- Incorporating Unlikely Negative Cues for Distinctive Image Captioning3
A plug-and-play framework incorporating unlikely negative knowledge that focuses on preventing the model from producing undesirable generic descriptions while addressing previous limitations is introduced to improve image captioning by integrating negative knowledge.
- 3
- Meta-Ensemble Parameter Learning3
WeightFormer is introduced, a Transformer-based model that can predict student network weights layer by layer in a forward pass, according to the teacher model parameters, which can potentially lead to a new, more efficient, and scalable paradigm of ensemble networks parameter learning.
- Visual Attributes for Fashion Analytics2
This chapter describes a cross-domain clothing retrieval system, which receives as input a user photo of a particular clothing item taken in unconstrained conditions, and retrieves the exact same or similar item from online shopping catalogs.
- 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 2026-10-15. 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.