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
- Kate SaenkoSuggested from co-authorship
- Stan SclaroffSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works48 from public data
- 704
- Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters311
This work presents a parameter-efficient continual learning framework to alleviate long-term forgetting in incremental learning with vision-language models, and introduces a Distribution Discriminative Auto-Selector (DDAS) that automatically routes in-distribution and out-of-distribution inputs to the MoE Adapter and the original CLIP, respectively.
- Temporally Distributed Networks for Fast Video Semantic Segmentation224
TDNet, a temporally distributed network designed for fast and accurate video semantic segmentation, is presented, observing that features extracted from a certain high-level layer of a deep CNN can be approximated by composing features extracts from several shallower sub-networks.
- DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations200
The strong alignment of textual and visual features pretrained with millions of auxiliary image-text pairs is utilized and Dual Context Optimization (DualCoOp) is proposed as a unified framework for partial-label MLR and zero-shot MLR.
- Real-Time Semantic Segmentation With Fast Attention163
The proposed architecture relies on the fast spatial attention, which is a simple yet efficient modification of the popular self-attention mechanism and captures the same rich spatial context at a small fraction of the computational cost, by changing the order of operations.
- 117
- ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes100
This paper presents the first in-the-wild industrial-grade waste detection and segmentation dataset, ZeroWaste, which it is believed will catalyze research in object detection and semantic segmentation in extreme clutter as well as applications in the recycling domain.
- Many-to-many Splatting for Efficient Video Frame Interpolation82
This work proposes a fully differentiable Many-to-Many (M2M) splatting framework to interpolate frames efficiently and finds that it significantly improves the efficiency while maintaining high effectiveness.
- Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation79
This paper proposes a novel framework that learns to discriminate noisy samples based on Bayesian uncertainty estimation and achieves significant accuracy improvement over previous approaches for large-scale open-set segmentation.
- Koala: Key Frame-Conditioned Long Video-LLM75
This work proposes a lightweight and self-supervised approach, Key frame-conditioned long video-LLM (Koala), that introduces learnable spatiotemporal queries to adapt pretrained vLLMs for generalizing to longer videos and empirically shows that this approach not only helps a pretrained vLLM to understand long videos but also improves its accuracy on short-term action recognition.
- Learning to Detect Every Thing in an Open World64
LDET leads to significant improvements on many datasets in the open-world instance segmentation task, outperforming baselines on cross-category generalization on COCO, as well as cross-dataset evaluation on UVO and Cityscapes.
- 58
- AVN: An Adversarial Variation Network Model for Handwritten Signature Verification49
A novel adversarial variation network (AVN) model for handwritten signature verification which mines effective features by actively varying existing data and generating new data and therefore the signature verification performance is improved.
- DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition With Limited Annotations44
An efficient and effective framework called Evidence-guided Dual Context Optimization (DualCoOp++), which serves as a unified approach for addressing partial-label and zero-shot multi-label recognition and introduces a Winner-Take-All module that promotes inter-class interaction during training, while avoiding the need for extra parameters and costs.
- On Efficient Variants of Segment Anything Model: A Survey39
This survey provides the first comprehensive review of efficient SAM variants across various hardware, assessing their efficiency and accuracy on representative benchmarks, and providing a clear comparison of their overall performance.
- Splatting-based Synthesis for Video Frame Interpolation32
A deep learning approach that solely relies on splatting to synthesize interpolated frames for video frame interpolation is proposed, which is not only much faster than similar approaches, especially for multi-frame interpolation, but can also yield new state-of-the-art results at high resolutions.
- 25
- 23
- 20
- 14
- 13
- Video Frame Interpolation With Many-to-Many Splatting and Spatial Selective Refinement12
This work proposes a fully differentiable Many-to-Many (M2M) splatting framework to interpolate frames efficiently and extends an M2M++ framework by introducing a flexible Spatial Selective Refinement (SSR) component, which allows for trading computational efficiency for interpolation quality and vice versa.
- 9
- 8
- Token Boosting for Robust Self-Supervised Visual Transformer Pre-training8
The Token Boosting Module (TBM) is introduced as a plug-and-play component for VTs that effectively allows the VT to learn to extract clean and robust features during masked autoencoding pre-training, and theoretical analysis is provided to show how TBM improves model pre- training with more robust and generalizable representations, thus benefiting down stream tasks.
- 8
- 7
- 7
- Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weather6
A novel Geometry-Reflectance Collaboration (GRC) framework that explicitly separates feature extraction for geometry and reflectance, achieving better robustness and generalization in adverse weather conditions and establishes new state-of-the-art results.
- 6
- 6
- DreamMix: Decoupling Object Attributes for Enhanced Editability in Customized Image Inpainting5
Extensive experiments across multiple inpainting backbones demonstrate that DreamMix achieves a superior balance between identity preservation and attribute editability across diverse applications, including object insertion, attribute editing, and small object inpainting.
- Adaptive Multi-Modality Prompt Learning5
This paper employs previous text prompt learning and proposes a new image prompt learning, which achieves in-sample and out-of-sample generalization, by first masking meaningless patches and then padding them with the learnable parameters and the information from texts.
- Seeking Proxy Point via Stable Feature Space for Noisy Correspondence Learning3
This work proposes a novel framework: Seeking Proxy Point via Stable Feature Space (SPS), which employs a fine-grained partitioning strategy to obtain a high-confidence reliable set and achieves robust learning under Noisy Correspondence.
- 3
- 2
- 2
- –
- –
- Explicit Geometry-Reflectance Domain Shift Modeling for Robust LiDAR Segmentation in Adverse Weather–
The Geometry–Reflectance Collaboration Network (GRCNet) is introduced, which separately encodes geometry and reflectance and fuses them via robust multi-level feature collaboration to suppress weather-induced corruption while preserving complementary semantics.
- –
- –
- –
- –
- –
- –
- –
- –
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.