6 papers · 1 filter
SignMAE: Segmentation-Driven Self-Supervised Learning for Sign Language Recognition
Kunyuan Xie, Zhixi Cai, Kalin Stefanov
Subtle hand differences make sign language recognition challenging, yet many existing methods rely on encoders pretrained on generic action datasets that poorly capture such fine-g…
DexAvatar: 3D Sign Language Reconstruction with Hand and Body Pose Priors
Kaustubh Kundu, Hrishav Bakul Barua, Lucy Robertson-Bell +2
The trend in sign language generation is centered around data-driven generative methods that require vast amounts of precise 2D and 3D human pose data to achieve an acceptable gene…
Do Blind Spots Matter for Word-Referent Mapping? A Computational Study with Infant Egocentric Video
Zekai Shi, Zhixi Cai, Kalin Stefanov
Typically, children start to learn their first words between 6 and 9 months, linking spoken utterances to their visual referents. Without prior knowledge, a word encountered for th…
A Cycle Ride to HDR: Semantics Aware Self-Supervised Framework for Unpaired LDR-to-HDR Image Reconstruction
Hrishav Bakul Barua, Kalin Stefanov, Lemuel Lai En Che +3
Reconstruction of High Dynamic Range (HDR) from Low Dynamic Range (LDR) images is an important computer vision task. There is a significant amount of research utilizing both conven…
1M-Deepfakes Detection Challenge
Zhixi Cai, Abhinav Dhall, Shreya Ghosh +4
The detection and localization of deepfake content, particularly when small fake segments are seamlessly mixed with real videos, remains a significant challenge in the field of dig…
Webcam-based Eye Gaze Tracking under Natural Head Movement
Kalin Stefanov
This manuscript investigates and proposes a visual gaze tracker that tackles the problem using only an ordinary web camera and no prior knowledge in any sense (scene set-up, camera…