Publications
Insights to Staqu's Publications Shedding Light On Our Research Work
Our Publications
- Jan 2020
Frequency and Temporal Convolutional Attention for Text-Independent Speaker Recognition
Majority of the recent approaches for text…
S. Yadav and A. Rai, accepted for presentation at ICASSP 2020
- October 2018
Diversity in Fashion Recommendation Using Semantic Parsing
Developing recommendation system for fashion images is challenging due to the inherent…
S. Verma, S. Anand, C. Arora, and A. Rai, Proc. ICIP 2018, IEEE
- October 2018
Exploiting Texture Cues for Clothing Parsing in Fashion Images
Exploiting the texture for recognizing the clothing type…
T. Khurana, K. Mahajan, C. Arora, and A. Rai, Proc. ICIP 2018, IEEE
- September 2018
Learning Discriminative Features for Speaker Identification and Verification
The success of any Text Independent Speaker Identification and/or Verification system…
S. Yadav and A. Rai, in Interspeech
- September 2018
Pose Aware Fine-Grained Visual Classification Using Pose Experts
We observe an important and often ignored additional structure present in an FGVC…
K. Mahajan, T. Khurana, A. Chopra, I. Gupta, C. Arora, and A. Rai Proc. ICIP 2018, IEEE
- April 2024
ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation
It proposes a diffusion-based monocular depth estimation framework which achieves state-of-the-art accuracy on NYU Depth v2 and KITTI while significantly improving zero-shot generalization across multiple unseen datasets.
S. Patni, A. Agarwal, and C. Arora, accepted at CVPR 2024
Our Patents
- November 2015
Large Scale Image Retrieval based on Image and Sketch based Queries
- November 2015