Syed Talal Wasim

9

Papers

7

Total Citations

Papers (9)

GroupMamba: Efficient Group-Based Visual State Space Model

Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models

MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation

Vita-CLIP: Video and Text Adaptive CLIP via Multimodal Prompting

Self-regulating Prompts: Foundational Model Adaptation without Forgetting

Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition

VideoGrounding-DINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding

STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security Inspection

Hardware Resilience Properties of Text-Guided Image Classifiers