Publications

You can also find my articles on my Google Scholar profile.

*Equal Authors / Highlighted Papers

MotionFormer: An Improved Transformer-Based Architecture for Multi-object Tracking

*Harshit Agarwal,*Agrya Halder, and Pratik Chattopadhyay,
8th International Conference, CVIP 2023Paper

Awarded Best Paper in CVIP 2023 IIT Jammu

MotionFormer is a novel variant of the TrackFormer model that addresses the limitations in scenarios involving short-term object occlusion, camera motion, and ambiguous detection especially in low frame-rate videos. MotionFormer, integrating an online motion prediction module based on the Kalman Filter, incorporates the important temporal information present in the videos. The addition of the Kalman Filter helps the model study the tracked pedestrians’ motion patterns and leverage them for effective association among targets across the video frames even in the case of short-term occlusions without adding much to the computational complexity of the overall framework.

Gait transformation network for gait de-identification with pose preservation

Agrya Halder, Pratik Chattopadhyay, and Sathish Kumar,
Springer SIVP 2022Paper

GTNet is a plausible deep learning-based solution to the gait de-identification problem. First, a set of key walking poses is determined from a large gallery set. Next, given an input sequence, a graph-based path search algorithm is employed to classify each frame of the sequence into the appropriate key pose. Next, a random frame with matched key pose chosen from the subset of the gallery sequences is considered the target frame. The dense pose features of the input and target frames are then fused using the proposed gait transformation network (GTNet).