2 citations · 4 across the 24 of their papers we have counts for
14 papers · 1 filter
Beyond Global Editing: Per-Instance Disentangled Subspaces for Training-Free Hallucination Mitigation in LVLMs
Ali Cheraghian, Hamidreza Dastmalchi, Hamed Barzamini +4
Recent advances in large vision-language models (LVLMs) have enabled powerful multimodal reasoning by integrating visual encoders with large language models (LLMs). However, their…
A Point Cloud Transformer for Remote Monitoring and Automated Assessment of Physical Rehabilitation Exercises
Kazi Rafat, Md. Ismail Hossain, M M Lutfe Elahi +4
Rehabilitation exercises are essential in restoring lost physical functions of patients suffering from various diseases (e.g., Parkinson's, back pain). Carrying out these rehabilit…
Beyond Real Weights: Hypercomplex Representations for Stable Quantization
Jawad Ibn Ahad, Maisha Rahman, Amrijit Biswas +5
Multimodal language models (MLLMs) require large parameter capacity to align high-dimensional visual features with linguistic representations, making them computationally heavy and…
Teacher-Guided One-Shot Pruning via Context-Aware Knowledge Distillation
Md. Samiul Alim, Sharjil Khan, Amrijit Biswas +3
Unstructured pruning remains a powerful strategy for compressing deep neural networks, yet it often demands iterative train-prune-retrain cycles, resulting in significant computati…
Label Semantics for Robust Hyperspectral Image Classification
Rafin Hassan, Zarin Tasnim Roshni, Rafiqul Bari +4
Hyperspectral imaging (HSI) classification is a critical tool with widespread applications across diverse fields such as agriculture, environmental monitoring, medicine, and materi…
HadaSmileNet: Hadamard fusion of handcrafted and deep-learning features for enhancing facial emotion recognition of genuine smiles
Mohammad Junayed Hasan, Nabeel Mohammed, Shafin Rahman +1
The distinction between genuine and posed emotions represents a fundamental pattern recognition challenge with significant implications for data mining applications in social scien…
VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval
Dhiman Paul, Md Rizwan Parvez, Nabeel Mohammed +1
Prevailing joint prediction transformers for Video Highlight Detection and Moment Retrieval (HD/MR) exhibit deficiencies in handling cross-task dynamics, achieving robust video-tex…
Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models
Hamidreza Dastmalchi, Aijun An, Ali Cheraghian +2
Test-time adaptation (TTA) of 3D point clouds is crucial for mitigating discrepancies between training and testing samples in real-world scenarios, particularly when handling corru…
Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor
Sahar Ahmadi, Ali Cheraghian, Morteza Saberi +4
Recent advances in deep learning for processing point clouds hold increased interest in Few-Shot Class Incremental Learning (FSCIL) for 3D computer vision. This paper introduces a…
3D Point Cloud Network Pruning: When Some Weights Do not Matter
Amrijit Biswas, Md. Ismail Hossain, M M Lutfe Elahi +4
A point cloud is a crucial geometric data structure utilized in numerous applications. The adoption of deep neural networks referred to as Point Cloud Neural Networks (PC- NNs), fo…
Backpropagation-free Network for 3D Test-time Adaptation
Yanshuo Wang, Ali Cheraghian, Zeeshan Hayder +7
Real-world systems often encounter new data over time, which leads to experiencing target domain shifts. Existing Test-Time Adaptation (TTA) methods tend to apply computationally h…
Continual Test-time Domain Adaptation via Dynamic Sample Selection
Yanshuo Wang, Jie Hong, Ali Cheraghian +4
The objective of Continual Test-time Domain Adaptation (CTDA) is to gradually adapt a pre-trained model to a sequence of target domains without accessing the source data. This pape…
ChatGPT-guided Semantics for Zero-shot Learning
Fahimul Hoque Shubho, Townim Faisal Chowdhury, Ali Cheraghian +3
Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes…
LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit Calibration
Md. Ismail Hossain, M M Lutfe Elahi, Sameera Ramasinghe +4
In the knowledge distillation literature, feature-based methods have dominated due to their ability to effectively tap into extensive teacher models. In contrast, logit-based appro…