Picture for Dan Guo

Dan Guo

A Two-Stage Adverse Weather Semantic Segmentation Method for WeatherProof Challenge CVPR 2024 Workshop UG2+

Jun 08, 2024
Viaarxiv icon

Joint Spatial-Temporal Modeling and Contrastive Learning for Self-supervised Heart Rate Measurement

Jun 07, 2024
Viaarxiv icon

Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling

Jun 03, 2024
Viaarxiv icon

The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report

Add code
Apr 16, 2024
Figure 1 for The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
Figure 2 for The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
Figure 3 for The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
Figure 4 for The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
Viaarxiv icon

Unified Static and Dynamic Network: Efficient Temporal Filtering for Video Grounding

Add code
Mar 21, 2024
Figure 1 for Unified Static and Dynamic Network: Efficient Temporal Filtering for Video Grounding
Figure 2 for Unified Static and Dynamic Network: Efficient Temporal Filtering for Video Grounding
Figure 3 for Unified Static and Dynamic Network: Efficient Temporal Filtering for Video Grounding
Figure 4 for Unified Static and Dynamic Network: Efficient Temporal Filtering for Video Grounding
Viaarxiv icon

Training A Small Emotional Vision Language Model for Visual Art Comprehension

Add code
Mar 17, 2024
Figure 1 for Training A Small Emotional Vision Language Model for Visual Art Comprehension
Figure 2 for Training A Small Emotional Vision Language Model for Visual Art Comprehension
Figure 3 for Training A Small Emotional Vision Language Model for Visual Art Comprehension
Figure 4 for Training A Small Emotional Vision Language Model for Visual Art Comprehension
Viaarxiv icon

Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture

Add code
Mar 12, 2024
Figure 1 for Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture
Figure 2 for Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture
Figure 3 for Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture
Figure 4 for Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture
Viaarxiv icon

Benchmarking Micro-action Recognition: Dataset, Methods, and Applications

Add code
Mar 08, 2024
Figure 1 for Benchmarking Micro-action Recognition: Dataset, Methods, and Applications
Figure 2 for Benchmarking Micro-action Recognition: Dataset, Methods, and Applications
Figure 3 for Benchmarking Micro-action Recognition: Dataset, Methods, and Applications
Figure 4 for Benchmarking Micro-action Recognition: Dataset, Methods, and Applications
Viaarxiv icon

Object-aware Adaptive-Positivity Learning for Audio-Visual Question Answering

Add code
Dec 20, 2023
Viaarxiv icon

EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer

Add code
Dec 07, 2023
Figure 1 for EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer
Figure 2 for EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer
Figure 3 for EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer
Figure 4 for EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer
Viaarxiv icon