5 papers
DenVisCoM: Dense Vision Correspondence Mamba for Efficient and Real-time Optical Flow and Stereo Estimation
Tushar Anand, Maheswar Bora, Antitza Dantcheva +1
In this work, we propose a novel Mamba block DenVisCoM, as well as a novel hybrid architecture specifically tailored for accurate and real-time estimation of optical flow and dispa…
Do You See What I Say? Generalizable Deepfake Detection based on Visual Speech Recognition
Maheswar Bora, Tashvik Dhamija, Shukesh Reddy +4
Deepfake generation has witnessed remarkable progress, contributing to highly realistic generated images, videos, and audio. While technically intriguing, such progress has raised…
ViM-Disparity: Bridging the Gap of Speed, Accuracy and Memory for Disparity Map Generation
Maheswar Bora, Tushar Anand, Saurabh Atreya +2
In this work we propose a Visual Mamba (ViM) based architecture, to dissolve the existing trade-off for real-time and accurate model with low computation overhead for disparity map…
KDC-MAE: Knowledge Distilled Contrastive Mask Auto-Encoder
Maheswar Bora, Saurabh Atreya, Aritra Mukherjee +1
In this work, we attempted to extend the thought and showcase a way forward for the Self-supervised Learning (SSL) learning paradigm by combining contrastive learning, self-distill…
Enhancing 3D-Air Signature by Pen Tip Tail Trajectory Awareness: Dataset and Featuring by Novel Spatio-temporal CNN
Saurabh Atreya, Maheswar Bora, Aritra Mukherjee +1
This work proposes a novel process of using pen tip and tail 3D trajectory for air signature. To acquire the trajectories we developed a new pen tool and a stereo camera was used.…