Deepti Ghadiyaram

56 papers A* 10B 3Misc 3Journal 34Unranked 6
YearRankTypeTitle / Venue / Authors
2026 J jnl
DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers.
CoRR
Dahye Kim, Deepti Ghadiyaram, Raghudeep Gadde
2026 J jnl
Seeing Isn't Orienting: A Cognitively Grounded Benchmark Reveals Systematic Orientation Failures in MLLMs Supplementary.
CoRR
Nazia Tasnim, Keanu Nichols, Yuting Yan, Nicholas Ikechukwu, Elva Zou, Deepti Ghadiyaram, Bryan A. Plummer
2025 J jnl
Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations.
CoRR
Dahye Kim, Deepti Ghadiyaram
2025 J jnl
DebiasPI: Inference-time Debiasing by Prompt Iteration of a Text-to-Image Generative Model.
CoRR
Sarah Bonna, Yu-Cheng Huang, Ekaterina Novozhilova, Sejin Paik, Zhengyang Shan, Michelle Yilin Feng, Ge Gao, Yonish Tayal, Rushil Kulkarni, Jialin Yu, Nupur Divekar, Deepti Ghadiyaram, Derry Wijaya, Margrit Betke
2025 J jnl
Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos.
CoRR
Xavier Thomas, Youngsun Lim, Ananya Srinivasan, Audrey Zheng, Deepti Ghadiyaram
2025 J jnl
Improving Physical Object State Representation in Text-to-Image Generative Systems.
CoRR
Tianle Chen, Chaitanya Chakka, Deepti Ghadiyaram
2025 J jnl
Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative Models.
CoRR
Ketan Suhaas Saichandran, Xavier Thomas, Prakhar Kaushik, Deepti Ghadiyaram
2025 J jnl
Right Side Up? Disentangling Orientation Understanding in MLLMs with Fine-grained Multi-axis Perception Tasks.
CoRR
Keanu Nichols, Nazia Tasnim, Yuting Yan, Nicholas Ikechukwu, Elva Zou, Deepti Ghadiyaram, Bryan A. Plummer
2025 J jnl
Some Modalities are More Equal Than Others: Decoding and Architecting Multimodal Integration in MLLMs.
CoRR
Tianle Chen, Chaitanya Chakka, Arjun Reddy Akula, Xavier Thomas, Deepti Ghadiyaram
2025 J jnl
What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization.
CoRR
Xavier Thomas, Deepti Ghadiyaram
2024 — conf
DebiasPI: Inference-Time Debiasing by Prompt Iteration of a Text-to-Image Generative Model.
ECCV Workshops (21)
Sarah Bonna, Yu-Cheng Huang, Ekaterina Novozhilova, Sejin Paik, Zhengyang Shan, Michelle Yilin Feng, Ge Gao, Yonish Tayal, Rushil Kulkarni, Jialin Yu, Nupur Divekar, Deepti Ghadiyaram, Derry Wijaya, Margrit Betke
2023 J jnl
Beyond web-scraping: Crowd-sourcing a geographically diverse image dataset.
CoRR
Vikram V. Ramaswamy, Sing Yu Lin, Dora Zhao, Aaron B. Adcock, Laurens van der Maaten, Deepti Ghadiyaram, Olga Russakovsky
2023 A* conf
GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition.
NeurIPS
Vikram V. Ramaswamy, Sing Yu Lin, Dora Zhao, Aaron Adcock, Laurens van der Maaten, Deepti Ghadiyaram, Olga Russakovsky
2023 J jnl
Helping Visually Impaired People Take Better Quality Pictures.
CoRR
Maniratnam Mandal, Deepti Ghadiyaram, Danna Gurari, Alan C. Bovik
2023 J jnl
Helping Visually Impaired People Take Better Quality Pictures.
IEEE Trans. Image Process.
Maniratnam Mandal, Deepti Ghadiyaram, Danna Gurari, Alan C. Bovik
2023 J jnl
Mitigating stereotypical biases in text to image generative systems.
CoRR
Piero Esposito, Parmida Atighehchian, Anastasis Germanidis, Deepti Ghadiyaram
2022 — conf
Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals.
ECCV (12)
Simon Vandenhende, Dhruv Mahajan, Filip Radenovic, Deepti Ghadiyaram
2022 J jnl
Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals.
CoRR
Simon Vandenhende, Dhruv Mahajan, Filip Radenovic, Deepti Ghadiyaram
2022 — conf
Telepresence Video Quality Assessment.
ECCV (37)
Zhenqiang Ying, Deepti Ghadiyaram, Alan C. Bovik
2022 J jnl
Telepresence Video Quality Assessment.
CoRR
Zhenqiang Ying, Deepti Ghadiyaram, Alan C. Bovik
2021 A* conf
Generic Event Boundary Detection: A Benchmark for Event Segmentation.
ICCV
Mike Zheng Shou, Stan Weixian Lei, Weiyao Wang, Deepti Ghadiyaram, Matt Feiszli
2021 J jnl
Generic Event Boundary Detection: A Benchmark for Event Segmentation.
CoRR
Mike Zheng Shou, Deepti Ghadiyaram, Weiyao Wang, Matt Feiszli
2021 A* conf
How2Sign: A Large-Scale Multimodal Dataset for Continuous American Sign Language.
CVPR
Amanda Cardoso Duarte, Shruti Palaskar, Lucas Ventura, Deepti Ghadiyaram, Kenneth DeHaan, Florian Metze, Jordi Torres, Xavier Giró-i-Nieto
2021 A* conf
Patch-VQ: 'Patching Up' the Video Quality Problem.
CVPR
Zhenqiang Ying, Maniratnam Mandal, Deepti Ghadiyaram, Alan C. Bovik
2020 A* conf
ClusterFit: Improving Generalization of Visual Representations.
CVPR
Xueting Yan, Ishan Misra, Abhinav Gupta, Deepti Ghadiyaram, Dhruv Mahajan
2020 A* conf
Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias.
CVPR
Krishna Kumar Singh, Dhruv Mahajan, Kristen Grauman, Yong Jae Lee, Matt Feiszli, Deepti Ghadiyaram
2020 J jnl
Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias.
CoRR
Krishna Kumar Singh, Dhruv Mahajan, Kristen Grauman, Yong Jae Lee, Matt Feiszli, Deepti Ghadiyaram
2020 A* conf
From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality.
CVPR
Zhenqiang Ying, Haoran Niu, Praful Gupta, Dhruv Mahajan, Deepti Ghadiyaram, Alan C. Bovik
2020 J jnl
How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language.
CoRR
Amanda Cardoso Duarte, Shruti Palaskar, Deepti Ghadiyaram, Kenneth DeHaan, Florian Metze, Jordi Torres, Xavier Giró-i-Nieto
2020 J jnl
Patch-VQ: 'Patching Up' the Video Quality Problem.
CoRR
Zhenqiang Ying, Maniratnam Mandal, Deepti Ghadiyaram, Alan C. Bovik
2019 J jnl
A Subjective and Objective Study of Stalling Events in Mobile Streaming Videos.
IEEE Trans. Circuits Syst. Video Technol.
Deepti Ghadiyaram, Janice Pan, Alan C. Bovik
2019 A* conf
Activity Driven Weakly Supervised Object Detection.
CVPR
Zhenheng Yang, Dhruv Mahajan, Deepti Ghadiyaram, Ram Nevatia, Vignesh Ramanathan
2019 J jnl
Activity Driven Weakly Supervised Object Detection.
CoRR
Zhenheng Yang, Dhruv Mahajan, Deepti Ghadiyaram, Ram Nevatia, Vignesh Ramanathan
2019 J jnl
ClusterFit: Improving Generalization of Visual Representations.
CoRR
Xueting Yan, Ishan Misra, Abhinav Gupta, Deepti Ghadiyaram, Dhruv Mahajan
2019 J jnl
From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality.
CoRR
Zhenqiang Ying, Haoran Niu, Praful Gupta, Dhruv Mahajan, Deepti Ghadiyaram, Alan C. Bovik
2019 A* conf
Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition.
CVPR
Deepti Ghadiyaram, Du Tran, Dhruv Mahajan
2019 J jnl
Large-scale weakly-supervised pre-training for video action recognition.
CoRR
Deepti Ghadiyaram, Matt Feiszli, Du Tran, Xueting Yan, Heng Wang, Dhruv Mahajan
2019 A* conf
Less Is More: Learning Highlight Detection From Video Duration.
CVPR
Bo Xiong, Yannis Kalantidis, Deepti Ghadiyaram, Kristen Grauman
2019 J jnl
Less is More: Learning Highlight Detection from Video Duration.
CoRR
Bo Xiong, Yannis Kalantidis, Deepti Ghadiyaram, Kristen Grauman
2018 J jnl
In-Capture Mobile Video Distortions: A Study of Subjective Behavior and Objective Algorithms.
IEEE Trans. Circuits Syst. Video Technol.
Deepti Ghadiyaram, Janice Pan, Alan C. Bovik, Anush Krishna Moorthy, Prasanjit Panda, Kai-Chieh Yang
2018 J jnl
Learning a Continuous-Time Streaming Video QoE Model.
IEEE Trans. Image Process.
Deepti Ghadiyaram, Janice Pan, Alan C. Bovik
2017 B conf
A no-reference video quality predictor for compression and scaling artifacts.
ICIP
Deepti Ghadiyaram, Chao Chen, Sasi Inguva, Anil C. Kokaram
2017 J jnl
Deep Convolutional Neural Models for Picture-Quality Prediction: Challenges and Solutions to Data-Driven Image Quality Assessment.
IEEE Signal Process. Mag.
Jongyoo Kim, Hui Zeng, Deepti Ghadiyaram, Sanghoon Lee, Lei Zhang, Alan C. Bovik
2017 J jnl
Large-Scale Crowdsourced Study for Tone-Mapped HDR Pictures.
IEEE Trans. Image Process.
Debarati Kundu, Deepti Ghadiyaram, Alan C. Bovik, Brian L. Evans
2017 J jnl
No-Reference Quality Assessment of Tone-Mapped HDR Pictures.
IEEE Trans. Image Process.
Debarati Kundu, Deepti Ghadiyaram, Alan C. Bovik, Brian L. Evans
2017 Misc conf
Subjective and objective quality assessment of Mobile Videos with In-Capture distortions.
ICASSP
Deepti Ghadiyaram, Janice Pan, Alan C. Bovik, Anush K. Moorthy, Prasanjit Panda, Kai-Chieh Yang
2016 J jnl
Massive Online Crowdsourced Study of Subjective and Objective Picture Quality.
IEEE Trans. Image Process.
Deepti Ghadiyaram, Alan C. Bovik
2016 Misc conf
No-reference image quality assessment for high dynamic range images.
ACSSC
Debarati Kundu, Deepti Ghadiyaram, Alan C. Bovik, Brian L. Evans
2016 J jnl
Perceptual Quality Prediction on Authentically Distorted Images Using a Bag of Features Approach.
CoRR
Deepti Ghadiyaram, Alan C. Bovik
2015 — conf
Feature maps driven no-reference image quality prediction of authentically distorted images.
Human Vision and Electronic Imaging
Deepti Ghadiyaram, Alan C. Bovik
2015 J jnl
Massive Online Crowdsourced Study of Subjective and Objective Picture Quality.
CoRR
Deepti Ghadiyaram, Alan C. Bovik
2015 B conf
Scene statistics of authentically distorted images in perceptually relevant color spaces for blind image quality assessment.
ICIP
Deepti Ghadiyaram, Alan C. Bovik
2014 — conf
Blind image quality assessment on real distorted images using deep belief nets.
GlobalSIP
Deepti Ghadiyaram, Alan C. Bovik
2014 Misc conf
Crowdsourced study of subjective image quality.
ACSSC
Deepti Ghadiyaram, Alan C. Bovik
2014 B conf
Delivery quality score model for Internet video.
ICIP
Hojatollah Yeganeh, Roman C. Kordasiewicz, Michael Gallant, Deepti Ghadiyaram, Alan C. Bovik
2014 — conf
Study of the effects of stalling events on the quality of experience of mobile streaming videos.
GlobalSIP
Deepti Ghadiyaram, Alan C. Bovik, Hojatollah Yeganeh, Roman C. Kordasiewicz, Michael Gallant