[month] [year]

ICIP – 2021

Dr. Ravi Kiran Sarvadevabhatla and his students Pranay Gupta and Divyanshu Sharma presented a paper on Syntactically Guided Generative Embeddings for Zero Shot Skeleton Action Recognition at IEEE International Conference on Image Processing (ICIP-2021) held virtually from 19 – 22 September at Anchorage, Alaska.

Research work as explained by Dr. Ravi Kiran Sarvadevabhatla, Pranay Gupta and Divyanshu Sharma:

We introduce SynSE, a novel syntactically guided generative approach for Zero-Shot Learning (ZSL). Our end-to-end approach learns progressively refined generative embedding spaces constrained within and across the involved modalities (visual, language). The inter-modal constraints are defined between action sequence embedding and embeddings of Parts of Speech (PoS) tagged words in the corresponding action description. We deploy SynSE for the task of skeleton-based action sequence recognition. Our design choices enable SynSE to generalize compositionally, i.e., recognize sequences whose action descriptions contain words not encountered during training. We also extend our approach to the more challenging Generalized Zero-Shot Learning (GZSL) problem via a confidence-based gating mechanism. We are the first to present zero-shot skeleton action recognition results on the largescale NTU-60 and NTU-120 skeleton action datasets with multiple splits. Our results demonstrate SynSE’s state of the art performance in both ZSL and GZSL settings compared to strong baselines on the NTU-60 and NTU-120 datasets. 

Link to full paper – https://arxiv.org/pdf/2101.11530.pdf

 

IEEE ICIP is the world’s largest and most comprehensive technical conference focused on image and video processing and computer vision. This conference showcased world-class plenary speakers, tutorials, exhibits, special sessions, industry sessions, and women in engineering that creates an excellent forum to foster innovation and entrepreneurship. There were opportunities to network with the brightest minds in academia and industry from this field. 

Link to conference page – https://www.2021.ieeeicip.org/