3.6k citations · 10.7k across the 127 of their papers we have counts for
28 papers · 1 filter
Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook
Sajid Javed, Martin Danelljan, Fahad Shahbaz Khan +3
Accurate and robust visual object tracking is one of the most challenging and fundamental computer vision problems. It entails estimating the trajectory of the target in an image s…
Spatio-temporal Relation Modeling for Few-shot Action Recognition
Anirudh Thatipelli, Sanath Narayan, Salman Khan +3
We propose a novel few-shot action recognition framework, STRM, which enhances class-specific feature discriminability while simultaneously learning higher-order temporal represent…
DoodleFormer: Creative Sketch Drawing with Transformers
Ankan Kumar Bhunia, Salman Khan, Hisham Cholakkal +4
Creative sketching or doodling is an expressive activity, where imaginative and previously unseen depictions of everyday visual objects are drawn. Creative sketch image generation…
Self-supervised Video Transformer
Kanchana Ranasinghe, Muzammal Naseer, Salman Khan +2
In this paper, we propose self-supervised training for video transformers using unlabeled video data. From a given video, we create local and global spatiotemporal views with varyi…
OW-DETR: Open-world Detection Transformer
Akshita Gupta, Sanath Narayan, K J Joseph +3
Open-world object detection (OWOD) is a challenging computer vision problem, where the task is to detect a known set of object categories while simultaneously identifying unknown o…
Class-agnostic Object Detection with Multi-modal Transformer
Muhammad Maaz, Hanoona Rasheed, Salman Khan +3
What constitutes an object? This has been a long-standing question in computer vision. Towards this goal, numerous learning-free and learning-based approaches have been developed t…
Restormer: Efficient Transformer for High-Resolution Image Restoration
Syed Waqas Zamir, Aditya Arora, Salman Khan +3
Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoratio…
Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection
Nicolae-Catalin Ristea, Neelu Madan, Radu Tudor Ionescu +4
Anomaly detection is commonly pursued as a one-class classification problem, where models can only learn from normal training samples, while being evaluated on both normal and abno…
UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection
Andra Acsintoae, Andrei Florescu, Mariana-Iuliana Georgescu +5
Detecting abnormal events in video is commonly framed as a one-class classification task, where training videos contain only normal events, while test videos encompass both normal…
CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for Non-Contrast to Contrast CT Translation
Nicolae-Catalin Ristea, Andreea-Iuliana Miron, Olivian Savencu +4
We propose a novel approach to translate unpaired contrast computed tomography (CT) scans to non-contrast CT scans and the other way around. Solving this task has two important app…
Dense Gaussian Processes for Few-Shot Segmentation
Joakim Johnander, Johan Edstedt, Michael Felsberg +2
Few-shot segmentation is a challenging dense prediction task, which entails segmenting a novel query image given only a small annotated support set. The key problem is thus to desi…
Discriminative Region-based Multi-Label Zero-Shot Learning
Sanath Narayan, Akshita Gupta, Salman Khan +3
Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image. However, the occurrence of…
Context-Conditional Adaptation for Recognizing Unseen Classes in Unseen Domains
Puneet Mangla, Shivam Chandhok, Vineeth N Balasubramanian +1
Recent progress towards designing models that can generalize to unseen domains (i.e domain generalization) or unseen classes (i.e zero-shot learning) has embarked interest towards…
Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains
Shivam Chandhok, Sanath Narayan, Hisham Cholakkal +4
The need to address the scarcity of task-specific annotated data has resulted in concerted efforts in recent years for specific settings such as zero-shot learning (ZSL) and domain…
On Improving Adversarial Transferability of Vision Transformers
Muzammal Naseer, Kanchana Ranasinghe, Salman Khan +2
Vision transformers (ViTs) process input images as sequences of patches via self-attention; a radically different architecture than convolutional neural networks (CNNs). This makes…
Intriguing Properties of Vision Transformers
Muzammal Naseer, Kanchana Ranasinghe, Salman Khan +3
Vision transformers (ViT) have demonstrated impressive performance across various machine vision problems. These models are based on multi-head self-attention mechanisms that can f…
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning
Mamshad Nayeem Rizve, Salman Khan, Fahad Shahbaz Khan +1
In many real-world problems, collecting a large number of labeled samples is infeasible. Few-shot learning (FSL) is the dominant approach to address this issue, where the objective…
Handwriting Transformers
Ankan Kumar Bhunia, Salman Khan, Hisham Cholakkal +3
We propose a novel transformer-based styled handwritten text image generation approach, HWT, that strives to learn both style-content entanglement as well as global and local writi…
MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains
Yaxing Wang, Abel Gonzalez-Garcia, Chenshen Wu +4
GANs largely increases the potential impact of generative models. Therefore, we propose a novel knowledge transfer method for generative models based on mining the knowledge that i…
Rich Semantics Improve Few-shot Learning
Mohamed Afham, Salman Khan, Muhammad Haris Khan +2
Human learning benefits from multi-modal inputs that often appear as rich semantics (e.g., description of an object's attributes while learning about it). This enables us to learn…
Deep Gaussian Processes for Few-Shot Segmentation
Joakim Johnander, Johan Edstedt, Martin Danelljan +2
Few-shot segmentation is a challenging task, requiring the extraction of a generalizable representation from only a few annotated samples, in order to segment novel query images. A…
Orthogonal Projection Loss
Kanchana Ranasinghe, Muzammal Naseer, Munawar Hayat +2
Deep neural networks have achieved remarkable performance on a range of classification tasks, with softmax cross-entropy (CE) loss emerging as the de-facto objective function. The…
Multi-Stage Progressive Image Restoration
Syed Waqas Zamir, Aditya Arora, Salman Khan +4
Image restoration tasks demand a complex balance between spatial details and high-level contextualized information while recovering images. In this paper, we propose a novel synerg…
On Generating Transferable Targeted Perturbations
Muzammal Naseer, Salman Khan, Munawar Hayat +2
While the untargeted black-box transferability of adversarial perturbations has been extensively studied before, changing an unseen model's decisions to a specific `targeted' class…