Publications

• Megha Mariam K.M, Aditya Arun, Zakaria Laskar, and C V Jawahar -  PhyEduVideo: A Benchmark for Evaluating Text-to-Video Models for Physics Education, In Winter Conference on Applications of Computer Vision (WACV), 2025 [ PDF ]

• Yash Arora, Aditya Arun, and C V Jawahar -  What is there in an Indian Thali?, In Indian Conference on Vision Graphics and Image Processing (ICVGIP), 2025 [ PDF ]

• Aditya Arun, C. V. Jawahar and M. Pawan Kumar -  Dissimilarity Coefficient based Weakly Supervised Object Detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, 15 - 21 June 2019, Long Beach, California, United States.[PDF]

• Aditya Arun, C. V. Jawahar and M. Pawan Kumar -  Learning Human Poses from Actions Proceedings of the British Machine Vision Conference, 03-06 Sep 2018, Northumbria[PDF]

Projects

• Learning Human Poses from Actions

  People Involved : Aditya Arun, C. V. Jawahar and M. Pawan Kumar

  We consider the task of learning to estimate human pose in still images. In order to avoid the high cost of full supervision, we propose to use a diverse data set, which consists of two types of annotations: (i) a small number of images are labeled using the expensive ground-truth pose; and (ii) other images are labeled using the inexpensive action label. As action information helps narrow down the pose of a human, we argue that this approach can help reduce the cost of training without significantly affecting the accuracy.