Picture for Armin Mustafa

Armin Mustafa

RenDetNet: Weakly-supervised Shadow Detection with Shadow Caster Verification

Add code
Aug 30, 2024
Viaarxiv icon

Attend-Fusion: Efficient Audio-Visual Fusion for Video Classification

Add code
Aug 26, 2024
Figure 1 for Attend-Fusion: Efficient Audio-Visual Fusion for Video Classification
Figure 2 for Attend-Fusion: Efficient Audio-Visual Fusion for Video Classification
Figure 3 for Attend-Fusion: Efficient Audio-Visual Fusion for Video Classification
Figure 4 for Attend-Fusion: Efficient Audio-Visual Fusion for Video Classification
Viaarxiv icon

Single-image coherent reconstruction of objects and humans

Add code
Aug 15, 2024
Viaarxiv icon

NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative

Add code
Jun 10, 2024
Viaarxiv icon

An Effective-Efficient Approach for Dense Multi-Label Action Detection

Add code
Jun 10, 2024
Figure 1 for An Effective-Efficient Approach for Dense Multi-Label Action Detection
Figure 2 for An Effective-Efficient Approach for Dense Multi-Label Action Detection
Figure 3 for An Effective-Efficient Approach for Dense Multi-Label Action Detection
Figure 4 for An Effective-Efficient Approach for Dense Multi-Label Action Detection
Viaarxiv icon

CoLeaF: A Contrastive-Collaborative Learning Framework for Weakly Supervised Audio-Visual Video Parsing

Add code
May 17, 2024
Viaarxiv icon

S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removal

Add code
Apr 18, 2024
Viaarxiv icon

ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNet

Add code
Dec 05, 2023
Viaarxiv icon

CAD -- Contextual Multi-modal Alignment for Dynamic AVQA

Add code
Oct 27, 2023
Viaarxiv icon

PAT: Position-Aware Transformer for Dense Multi-Label Action Detection

Add code
Aug 09, 2023
Viaarxiv icon