sajjad ahmed shaaz

Research

Work & Interests

Research assistant at CMATER Lab, Jadavpur University. Broadly interested in multimodal learning, efficient deep learning, and AI for embodied systems.


Publications


Research Areas

Multimodal Deepfake Detection

Investigating audio-visual causal divergence as a signal for deepfake detection. Current work explores cross-modal synchrony via WhisperX forced phoneme alignment, CLIP ViT encoders, and Riemannian manifold representations of causal link integrity between modalities.

WhisperXCLIPRiemannian geometryCausal reasoningFakeAVCelebPolyGlotFake

Medical Image Classification

Dual-backbone deep learning architectures with attention mechanisms for robust medical image classification across pathology, histology, and radiology domains.

MobileNetV2DenseNet121Channel AttentionKnowledge DistillationLC25000BreakHis

On-Device AI & Model Compression

Deploying deep learning models on constrained hardware via structured pruning, quantization, and knowledge distillation. Current focus on FPGA deployment with Vitis AI and TADNet for task-aware open-vocabulary detection.

PruningINT8 QuantizationKnowledge DistillationVitis AIFPGACLIP

Autonomous Systems & Robotics

Computer vision pipelines and reinforcement learning for autonomous drone and rover systems. Includes GPS-resilient navigation via IMU-based dead reckoning and RL-based manipulator control.

YOLOStable-Baselines3PPOMAVLinkDead ReckoningROS

Interested in collaborating? Reach out.