Muhammad Kamran Janjua

Art is Long; Time is Fleeting!

I am a Machine Learning Researcher @ Huawei, Canada. I work on video understanding and online learning problems. Previously, I was a graduate student at University of Alberta, where I worked on continual learning.

Email  /  CV  /  Google Scholar  /  Github

I am interested in problems in perception and learning.

We argue that, in problems where vision tools can provide the necessary visual cues, the bottleneck is how tool outputs are represented ("representation mismatch"). We introduce Perception Programs, a training-free, model-agnostic method that rewrites tool outputs into compact, structured, language-native summaries that MLLMs can directly parse and reason over.

We propose a novel task of Distortion Graph (DG). DG treats paired images as a structured topology grounded in regions, and represents dense degradation information such as distortion type, severity, comparison and quality score in a compact interpretable graph structure.

We propose an all-in-one video restoration framework that grounds degradation-aware semantic context of video frames in natural language via foundation models, offering interpretable and flexible guidance.

We propose Turtle to learn the truncated causal history model for online video processing. The causal design in Turtle enables recurrence in inference through state-memorized historical features while allowing parallel training by sampling truncated video clips. We report new state-of-the-art results on a multitude of video restoration benchmark tasks.

We present CascadedGaze Network (CGNet), an encoder-decoder architecture that employs Global Context Extractor (GCE), a novel and efficient way to learn global information for image restoration.

We show the importance of learning in deployment, by comparing a TD agent trained purely offline with no online updating to a TD agent that learns online. This final result is one of the first to motivate the importance of adapting predictions in real-time, for non-stationary high-volume systems in the real world.