10 citations · 25 across the 13 of their papers we have counts for
15 papers
Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs
Muhammad Kamran Janjua, Hugo Silva, Di Niu +1
Multimodal language models (MLLMs) are increasingly paired with vision tools (e.g., depth, flow, correspondence) to enhance visual reasoning. However, despite access to these tool-…
Panoptic Pairwise Distortion Graph
Muhammad Kamran Janjua, Abdul Wahab, Bahador Rashidi
In this work, we introduce a new perspective on comparative image assessment by representing an image pair as a structured composition of its regions. In contrast, existing methods…
Grounding Degradations in Natural Language for All-In-One Video Restoration
Muhammad Kamran Janjua, Amirhosein Ghasemabadi, Kunlin Zhang +3
In this work, we propose an all-in-one video restoration framework that grounds degradation-aware semantic context of video frames in natural language via foundation models, offeri…
Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone
Negar Hassanpour, Muhammad Kamran Janjua, Kunlin Zhang +4
Balancing competing objectives remains a fundamental challenge in multi-task learning (MTL), primarily due to conflicting gradients across individual tasks. A common solution relie…
Learning Truncated Causal History Model for Video Restoration
Amirhosein Ghasemabadi, Muhammad Kamran Janjua, Mohammad Salameh +1
One key challenge to video restoration is to model the transition dynamics of video frames governed by motion. In this work, we propose TURTLE to learn the truncated causal history…
CascadedGaze: Efficiency in Global Context Extraction for Image Restoration
Amirhosein Ghasemabadi, Muhammad Kamran Janjua, Mohammad Salameh +3
Image restoration tasks traditionally rely on convolutional neural networks. However, given the local nature of the convolutional operator, they struggle to capture global informat…
GVFs in the Real World: Making Predictions Online for Water Treatment
Muhammad Kamran Janjua, Haseeb Shah, Martha White +3
In this paper we investigate the use of reinforcement-learning based prediction approaches for a real drinking-water treatment plant. Developing such a prediction system is a criti…
Movement-induced Priors for Deep Stereo
Yuxin Hou, Muhammad Kamran Janjua, Juho Kannala +1
We propose a method for fusing stereo disparity estimation with movement-induced prior information. Instead of independent inference frame-by-frame, we formulate the problem as a n…
Deep Latent Space Learning for Cross-modal Mapping of Audio and Visual Signals
Shah Nawaz, Muhammad Kamran Janjua, Ignazio Gallo +2
We propose a novel deep training algorithm for joint representation of audio and visual information which consists of a single stream network (SSNet) coupled with a novel loss func…
Do Cross Modal Systems Leverage Semantic Relationships?
Shah Nawaz, Muhammad Kamran Janjua, Ignazio Gallo +3
Current cross-modal retrieval systems are evaluated using R@K measure which does not leverage semantic relationships rather strictly follows the manually marked image text query pa…
Learning Inward Scaled Hypersphere Embedding: Exploring Projections in Higher Dimensions
Muhammad Kamran Janjua, Shah Nawaz, Alessandro Calefati +1
Majority of the current dimensionality reduction or retrieval techniques rely on embedding the learned feature representations onto a computable metric space. Once the learned feat…
Image and Encoded Text Fusion for Multi-Modal Classification
Ignazio Gallo, Alessandro Calefati, Shah Nawaz +1
Multi-modal approaches employ data from multiple input streams such as textual and visual domains. Deep neural networks have been successfully employed for these approaches. In thi…
Seeing Colors: Learning Semantic Text Encoding for Classification
Shah Nawaz, Alessandro Calefati, Muhammad Kamran Janjua +1
The question we answer with this work is: can we convert a text document into an image to exploit best image classification models to classify documents? To answer this question we…
Git Loss for Deep Face Recognition
Alessandro Calefati, Muhammad Kamran Janjua, Shah Nawaz +1
Convolutional Neural Networks (CNNs) have been widely used in computer vision tasks, such as face recognition and verification, and have achieved state-of-the-art results due to th…
Revisiting Cross Modal Retrieval
Shah Nawaz, Muhammad Kamran Janjua, Alessandro Calefati +1
This paper proposes a cross-modal retrieval system that leverages on image and text encoding. Most multimodal architectures employ separate networks for each modality to capture th…