20 citations · 26 across the 11 of their papers we have counts for
14 papers
CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition
Tianchi Liu, Nicholas Moratelli, Khurram Azeem Hashmi +5
Feature distillation is usually expected to add to logit distillation. We find that this expectation does not hold for two common feature losses in compact multilingual automatic s…
VisionPsy-Nano: Improving Accuracy, Efficiency, and Reliability in On-Device Vision-Language Models
Khurram Azeem Hashmi, Mohammadreza Zolfaghari, Changdae Park +6
Sub-billion-parameter Vision-Language Models are increasingly viable for on-device deployment, yet compact model size alone does not guarantee usability. On a phone, such a model c…
VVitCutLER: Towards Unsupervised Object Detection and Segmentation in Videos
Zhijing Lu, Khurram Azeem Hashmi, Didier Stricker +1
Unsupervised pixel-level video understanding remains challenging in real-world scenarios, where motion blur, occlusion, and fast object dynamics often cause temporal drift and flic…
Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection
Khurram Azeem Hashmi, Talha Uddin Sheikh, Didier Stricker +1
The primary challenge in Video Object Detection (VOD) is effectively exploiting temporal information to enhance object representations. Traditional strategies, such as aggregating…
UnSupDLA: Towards Unsupervised Document Layout Analysis
Talha Uddin Sheikh, Tahira Shehzadi, Khurram Azeem Hashmi +2
Document layout analysis is a key area in document research, involving techniques like text mining and visual analysis. Despite various methods developed to tackle layout analysis,…
Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection
Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker +1
In this paper, we address the limitations of the DETR-based semi-supervised object detection (SSOD) framework, particularly focusing on the challenges posed by the quality of objec…
FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision
Khurram Azeem Hashmi, Goutham Kallempudi, Didier Stricker +1
Extracting useful visual cues for the downstream tasks is especially challenging under low-light vision. Prior works create enhanced representations by either correlating visual qu…
Object Detection with Transformers: A Review
Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker +1
The astounding performance of transformers in natural language processing (NLP) has motivated researchers to explore their applications in computer vision tasks. DEtection TRansfor…
Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images
Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker +2
This paper takes an important step in bridging the performance gap between DETR and R-CNN for graphical object detection. Existing graphical object detection approaches have enjoye…
Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer
Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker +2
Table detection is the task of classifying and localizing table objects within document images. With the recent development in deep learning methods, we observe remarkable success…
BoxMask: Revisiting Bounding Box Supervision for Video Object Detection
Khurram Azeem Hashmi, Alain Pagani, Didier Stricker +1
We present a new, simple yet effective approach to uplift video object detection. We observe that prior works operate on instance-level feature aggregation that imminently neglects…
Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection
Khurram Azeem Hashmi, Didier Stricker, Muhammamd Zeshan Afzal
This paper presents the novel idea of generating object proposals by leveraging temporal information for video object detection. The feature aggregation in modern region-based vide…
Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networks
Khurram Azeem Hashmi, Marcus Liwicki, Didier Stricker +3
The first phase of table recognition is to detect the tabular area in a document. Subsequently, the tabular structures are recognized in the second phase in order to extract inform…
Guided Table Structure Recognition through Anchor Optimization
Khurram Azeem Hashmi, Didier Stricker, Marcus Liwicki +2
This paper presents the novel approach towards table structure recognition by leveraging the guided anchors. The concept differs from current state-of-the-art approaches for table…