6 papers
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…
PhysHDR: When Lighting Meets Materials and Scene Geometry in HDR Reconstruction
Hrishav Bakul Barua, Kalin Stefanov, Ganesh Krishnasamy +2
Low Dynamic Range (LDR) to High Dynamic Range (HDR) image translation is a fundamental task in many computational vision problems. Numerous data-driven methods have been proposed t…
S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction
Mohammad Adiban, Kalin Stefanov, Sabato Marco Siniscalchi +1
We address the video prediction task by putting forth a novel model that combines (i) a novel hierarchical residual learning vector quantized variational autoencoder (HR-VQVAE), an…