Publications

(2023). OneFormer: One Transformer to Rule Universal Image Segmentation. CVPR 23.

Preprint PDF Code Poster Video

(2022). Keys to Better Image Inpainting: Structure and Texture Go Hand in Hand. WACV'23.

Preprint PDF Code

(2022). Language Guided Meta-Control for Embodied Instruction Following. Workshop CVPR'22.

PDF

(2022). On The Cross-Modal Transfer from Natural Language to Code through Adapter Modules. ICPC'22.

Preprint PDF

(2022). RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition. CVPR'22.

Preprint PDF Code

(2021). SeMask: Semantically Masked Transformers for Semantic Segmentation. Under Review.

Preprint PDF Code

(2021). Exploring Long tail Visual Relationship Recognition with Large Vocabulary. ICCV21.

Preprint PDF Code

(2020). Multimodal Multi-Task Financial Risk Forecasting. MM'20.

PDF Video

(2020). DEAP Cache: Deep Eviction Admission and Prefetching for Cache. Under Review.

Preprint Code

(2020). VacSIM: Learning Effective Strategies for COVID-19 Vaccine Distribution using Reinforcement Learning. Under Review.

PDF

(2020). Less Wrong COVID-19 Projections With Interactive Assumptions. Under Review.

PDF

(2020). Visual Relationship Detection using Scene Graphs: A Survey.

Preprint

(2020). Universal Adversarial Perturbations: A Survey.

Preprint

(2019). Revisiting CycleGAN for Semi-Supervised Segmentation. arXiv preprint, Submitted to WACV 2020.

Preprint Code

(2019). A Generative Adversarial Network based Ensemble Technique for Automatic Evaluation of Machine Synthesized Speech. ACPR 2019.

(2019). GAN-Tree: An Incrementally Learned Hierarchical Generative Framework for Multi-Modal Data Distributions. ICCV 2019.

Preprint Code Poster

(2018). An Attention Model for Group Level Emotion Recognition. ICMI 2018.

Preprint PDF Code Poster Slides