| 2026 | AAAI | From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge. | Hui Lu, Yi Yu, Song Xia, Yiming Yang, Deepu Rajan, Boon Poh Ng, Alex C. Kot, Xudong Jiang |
| 2026 | WACV | A-V Representation Learning via Audio Shift Prediction for Multimodal Deepfake Detection and Temporal Localization. | Ashutosh Anshul, Eng Siong Chng, Deepu Rajan |
| 2025 | CVPR | Chebyshev Attention Depth Permutation Texture Network with Latent Texture Attribute Loss. | Ravishankar Evani, Deepu Rajan, Shangbo Mao |
| 2025 | ICCV | Intra-Modal and Cross-Modal Synchronization for Audio-Visual Deepfake Detection and Temporal Localization. | Ashutosh Anshul, Shreyas Gopal, Deepu Rajan, Eng Siong Chng |
| 2025 | ICCV | Imore: Implicit Program-Guided Reasoning for Human Motion QA. | Chen Li, Chinthani Sugandhika, Ee Yeo Keat, Eric P. Xing, Hao Zhang, Hong Yang, Deepu Rajan, Basura Fernando |
| 2025 | ICLR | Action Sequence Augmentation for Action Anticipation. | Yihui Qiu, Deepu Rajan |
| 2025 | WACV | An Encoder-Agnostic Weakly Supervised Method For Describing Textures. | Shangbo Mao, Deepu Rajan |
| 2025 | WACV | Situational Scene Graph for Structured Human-Centric Situation Understanding. | Chinthani Sugandhika, Chen Li, Deepu Rajan, Basura Fernando |
| 2024 | ECCV | Multiscale Graph Texture Network. | Ravishankar Evani, Deepu Rajan, Shangbo Mao |
| 2024 | ICASSP | Cross-Modality and Within-Modality Regularization for Audio-Visual Deepfake Detection. | Heqing Zou, Meng Shen, Yuchen Hu, Chen Chen, Eng Siong Chng, Deepu Rajan |
| 2024 | ICPR | Improving Temporal Action Segmentation and Detection with Hierarchical Task Grammar. | Yihui Qiu, Deepu Rajan |
| 2023 | ACL | UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning. | Heqing Zou, Meng Shen, Chen Chen, Yuchen Hu, Deepu Rajan, Eng Siong Chng |
| 2022 | ICASSP | Speech Emotion Recognition with Co-Attention Based Multi-Level Acoustic Information. | Heqing Zou, Yuke Si, Chen Chen, Deepu Rajan, Eng Siong Chng |
| 2019 | PERCOM | Gaze Estimation Using Residual Neural Network. | En Teng Wong, Seanglidet Yean, Qingyao Hu, Bu-Sung Lee, Jigang Liu, Deepu Rajan |
| 2019 | VCIP | Comparative Convolutional Neural Network for Younger Face Identification. | Liangliang Wang, Deepu Rajan |
| 2016 | CVPR | Backtracking ScSPM Image Classifier for Weakly Supervised Top-Down Saliency. | Hisham Cholakkal, Jubin Johnson, Deepu Rajan |
| 2016 | ECCV | Feasibility Analysis of Eye Typing with a Standard Webcam. | Yi Liu, Bu-Sung Lee, Andrzej Sluzek, Deepu Rajan, Martin J. McKeown |
| 2016 | ICPR | Salient object detection in tracking shots. | Karthik Muthuswamy, Deepu Rajan |
| 2015 | BMVC | Top-down saliency with Locality-constrained Contextual Sparse Coding. | Hisham Cholakkal, Deepu Rajan, Jubin Johnson |
| 2015 | ICIP | Local feature embedding for supervised image classification. | Junxia Li, Deepu Rajan, Jian Yang |
| 2015 | VCIP | Temporal trimap propagation using motion-assisted shape blending. | Jubin Johnson, Deepu Rajan, Hisham Cholakkal |
| 2014 | BMVC | Sparse codes as Alpha Matte. | Jubin Johnson, Deepu Rajan, Hisham Cholakkal |
| 2013 | BMVC | Depth really Matters: Improving Visual Salient Region Detection with Depth. | Karthik Desingh, K. Madhava Krishna, Deepu Rajan, C. V. Jawahar |
| 2013 | CVPR | Improving Image Matting Using Comprehensive Sampling Sets. | Ehsan Shahrian, Deepu Rajan, Brian L. Price, Scott Cohen |
| 2012 | CVPR | Weighted color and texture sample selection for image matting. | Ehsan Shahrian, Deepu Rajan |
| 2012 | ICASSP | Sparse likelihood saliency detection. | Minh-Chau Hoang, Deepu Rajan |
| 2012 | ICASSP | Salient motion detection through state controllability. | Karthik Muthuswamy, Deepu Rajan |
| 2012 | MMM | Scene Signatures for Unconstrained News Video Stories. | Ehsan Younessian, Deepu Rajan |
| 2012 | MMM | Multi-modal Solution for Unconstrained News Story Retrieval. | Ehsan Younessian, Deepu Rajan |
| 2010 | ACCV | Sustained Observability for Salient Motion Detection. | Viswanath Gopalakrishnan, Yiqun Hu, Deepu Rajan |
| 2010 | ACCV | Unsupervised Feature Selection for Salient Object Detection. | Viswanath Gopalakrishnan, Yiqun Hu, Deepu Rajan |
| 2010 | ACCV | Salient Region Detection by Jointly Modeling Distinctness and Redundancy of Image Content. | Yiqun Hu, Zhixiang Ren, Deepu Rajan, Liang-Tien Chia |
| 2010 | ACCV | A Data-Driven Approach to Understanding Skill in Photographic Composition. | Todd S. Sachs, Ramakrishna Kakarala, Shannon Lee Castleman, Deepu Rajan |
| 2010 | BMVC | Embedding Visual Words into Concept Space for Action and Scene Recognition. | Behrouz Khadem, Elahe Farahzadeh, Deepu Rajan, Andrzej Sluzek |
| 2010 | CVPR | Object recognition by discriminative combinations of line segments and ellipses. | Alex Y. S. Chia, Susanto Rahardja, Deepu Rajan, Maylor K. H. Leung |
| 2010 | CVPR | Hybrid shift map for video retargeting. | Yiqun Hu, Deepu Rajan |
| 2010 | ICMLA | Multi-view Clustering of Visual Words Using Canonical Correlation Analysis for Human Action Recognition. | Behrouz Saghafi, Deepu Rajan |
| 2010 | ICPR | Image Retargeting in Compressed Domain. | O. V. Ramana Murthy, Karthik Muthuswamy, Deepu Rajan, Liang-Tien Chia |
| 2009 | CVPR | Random walks on graphs to model saliency in images. | Viswanath Gopalakrishnan, Yiqun Hu, Deepu Rajan |
| 2009 | ISM | Improved Keypoint Matching Method for Near-Duplicate Keyframe Retrieval. | Ehsan Younessian, Deepu Rajan, Chng Eng Siong |
| 2008 | ICIP | A split and merge based ellipse detector. | Alex Y. S. Chia, Deepu Rajan, Maylor K. H. Leung, Susanto Rahardja |
| 2008 | ICPR | Image classification: Are rule-based systems effective when classes are fixed and known? | Palaiahnakote Shivakumara, Deepu Rajan, Suresh Anand Sadananthan |
| 2006 | MMM | Affective content detection in sitcom using subtitle and audio. | Min Xu, Liang-Tien Chia, Haoran Yi, Deepu Rajan |
| 2005 | ICASSP | Global Motion Compensated Key Frame Extraction from Compressed Videos. | Haoran Yi, Deepu Rajan, Liang-Tien Chia |
| 2004 | IKE | Motion Histogram: A New Motion Feature to Index Motion Content in Video Segment. | Haoran Yi, Deepu Rajan, Liang-Tien Chia |
| 2003 | ICIP | Efficient image retrieval using MPEG-7 descriptors. | Surong Wang, Liang-Tien Chia, Deepu Rajan |
| 2003 | ICIP | A unified approach to detection of shot boundaries and subshots in compressed video. | Haoran Yi, Deepu Rajan, Liang-Tien Chia |
| 2001 | ICASSP | Generation of super-resolution images from blurred observations using Markov random fields. | Deepu Rajan, Subhasis Chaudhuri |
| 2001 | ICCV | Simultaneous Estimation of Super-Resolved Intensity and Depth Maps from Low Resolution Defocused Observations of a Scene. | Deepu Rajan, Subhasis Chaudhuri |
| 2000 | ICPR | A Perceptually Organized Method for Image Interpolation. | Deepu Rajan, Subhasis Chaudhuri |