Abhishek Aich

32 papers A* 7A 2Journal 19Unranked 4
YearRankTypeTitle / Venue / Authors
2025 — conf
Mapillary Vistas Validation for Fine-Grained Traffic Signs: A Benchmark Revealing Vision-Language Model Limitations.
ICCVW
Sparsh Garg, Abhishek Aich
2025 J jnl
Mapillary Vistas Validation for Fine-Grained Traffic Signs: A Benchmark Revealing Vision-Language Model Limitations.
CoRR
Sparsh Garg, Abhishek Aich
2025 A* conf
Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation.
ICLR
Abhishek Aich, Yumin Suh, Samuel Schulter, Manmohan Chandraker
2025 J jnl
iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning.
CoRR
Manyi Yao, Bingbing Zhuang, Sparsh Garg, Amit Roychowdhury, Christian R. Shelton, Manmohan Chandraker, Abhishek Aich
2024 J jnl
Efficient Transformer Encoders for Mask2Former-style models.
CoRR
Manyi Yao, Abhishek Aich, Yumin Suh, Amit Roy-Chowdhury, Christian R. Shelton, Manmohan Chandraker
2024 — conf
Improving the Efficiency-Accuracy Trade-off of DETR-Style Models in Practice.
CVPR Workshops
Yumin Suh, Dongwan Kim, Abhishek Aich, Samuel Schulter, Jong-Chyi Su, Bohyung Han, Manmohan Chandraker
2024 J jnl
Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation.
CoRR
Abhishek Aich, Yumin Suh, Samuel Schulter, Manmohan Chandraker
2024 J jnl
Resolving Inconsistent Semantics in Multi-Dataset Image Segmentation.
CoRR
Qilong Zhangli, Di Liu, Abhishek Aich, Dimitris N. Metaxas, Samuel Schulter
2023 A conf
Cross-Domain Video Anomaly Detection without Target Domain Adaptation.
WACV
Abhishek Aich, Kuan-Chuan Peng, Amit K. Roy-Chowdhury
2023 A* conf
Efficient Controllable Multi-Task Architectures.
ICCV
Abhishek Aich, Samuel Schulter, Amit K. Roy-Chowdhury, Manmohan Chandraker, Yumin Suh
2023 J jnl
Efficient Controllable Multi-Task Architectures.
CoRR
Abhishek Aich, Samuel Schulter, Amit K. Roy-Chowdhury, Manmohan Chandraker, Yumin Suh
2023 A conf
Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attacks.
WACV
Abhishek Aich, Shasha Li, Chengyu Song, M. Salman Asif, Srikanth V. Krishnamurthy, Amit K. Roy-Chowdhury
2022 J jnl
Cross-Domain Video Anomaly Detection without Target Domain Adaptation.
CoRR
Abhishek Aich, Kuan-Chuan Peng, Amit K. Roy-Chowdhury
2022 A* conf
GAMA: Generative Adversarial Multi-Object Scene Attacks.
NeurIPS
Abhishek Aich, Calvin-Khang Ta, Akash Gupta, Chengyu Song, Srikanth V. Krishnamurthy, M. Salman Asif, Amit Roy-Chowdhury
2022 J jnl
GAMA: Generative Adversarial Multi-Object Scene Attacks.
CoRR
Abhishek Aich, Calvin-Khang Ta, Akash Gupta, Chengyu Song, Srikanth V. Krishnamurthy, M. Salman Asif, Amit K. Roy-Chowdhury
2022 J jnl
Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attacks.
CoRR
Abhishek Aich, Shasha Li, Chengyu Song, M. Salman Asif, Srikanth V. Krishnamurthy, Amit K. Roy-Chowdhury
2022 J jnl
Poisson2Sparse: Self-Supervised Poisson Denoising From a Single Image.
CoRR
Calvin-Khang Ta, Abhishek Aich, Akash Gupta, Amit K. Roy-Chowdhury
2022 — conf
Poisson2Sparse: Self-supervised Poisson Denoising from a Single Image.
MICCAI (8)
Calvin-Khang Ta, Abhishek Aich, Akash Gupta, Amit K. Roy-Chowdhury
2021 A* conf
Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations.
NeurIPS
Shasha Li, Abhishek Aich, Shitong Zhu, M. Salman Asif, Chengyu Song, Amit K. Roy-Chowdhury, Srikanth V. Krishnamurthy
2021 J jnl
Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations.
CoRR
Shasha Li, Abhishek Aich, Shitong Zhu, M. Salman Asif, Chengyu Song, Amit K. Roy-Chowdhury, Srikanth V. Krishnamurthy
2021 J jnl
Deep Quantized Representation for Enhanced Reconstruction.
CoRR
Akash Gupta, Abhishek Aich, Kevin Rodriguez, G. Venugopala Reddy, Amit K. Roy-Chowdhury
2021 J jnl
Elastic Weight Consolidation (EWC): Nuts and Bolts.
CoRR
Abhishek Aich
2021 A* conf
Spatio-Temporal Representation Factorization for Video-based Person Re-Identification.
ICCV
Abhishek Aich, Meng Zheng, Srikrishna Karanam, Terrence Chen, Amit K. Roy-Chowdhury, Ziyan Wu
2021 J jnl
Spatio-Temporal Representation Factorization for Video-based Person Re-Identification.
CoRR
Abhishek Aich, Meng Zheng, Srikrishna Karanam, Terrence Chen, Amit K. Roy-Chowdhury, Ziyan Wu
2020 A* conf
ALANET: Adaptive Latent Attention Network for Joint Video Deblurring and Interpolation.
ACM Multimedia
Akash Gupta, Abhishek Aich, Amit K. Roy-Chowdhury
2020 J jnl
ALANET: Adaptive Latent Attention Network forJoint Video Deblurring and Interpolation.
CoRR
Akash Gupta, Abhishek Aich, Amit K. Roy-Chowdhury
2020 — conf
Deep Quantized Representation For Enhanced Reconstruction.
ISBI Workshops
Akash Gupta, Abhishek Aich, Kevin Rodriguez, G. Venugopala Reddy, Amit K. Roy-Chowdhury
2020 A* conf
Non-Adversarial Video Synthesis with Learned Priors.
CVPR
Abhishek Aich, Akash Gupta, Rameswar Panda, Rakib Hyder, M. Salman Asif, Amit K. Roy-Chowdhury
2020 J jnl
Non-Adversarial Video Synthesis with Learned Priors.
CoRR
Abhishek Aich, Akash Gupta, Rameswar Panda, Rakib Hyder, M. Salman Asif, Amit K. Roy-Chowdhury
2017 J jnl
A novel CS Beamformer root-MUSIC algorithm and its subspace deviation analysis.
CoRR
Abhishek Aich, P. Palanisamy
2017 J jnl
On application of OMP and CoSaMP algorithms for DOA estimation problem.
CoRR
Abhishek Aich, P. Palanisamy
2017 J jnl
On-Grid DOA Estimation Method Using Orthogonal Matching Pursuit.
CoRR
Abhishek Aich, P. Palanisamy