99 citations · 140 across the 19 of their papers we have counts for
22 papers
Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentation
Elham Amin Mansour, Ozan Unal, Suman Saha +2
The increasing relevance of panoptic segmentation is tied to the advancements in autonomous driving and AR/VR applications. However, the deployment of such models has been limited…
Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding
Ozan Unal, Christos Sakaridis, Suman Saha +1
3D visual grounding is the task of localizing the object in a 3D scene which is referred by a description in natural language. With a wide range of applications ranging from autono…
CS-Mixer: A Cross-Scale Vision MLP Model with Spatial-Channel Mixing
Jonathan Cui, David A. Araujo, Suman Saha +1
Despite their simpler information fusion designs compared with Vision Transformers and Convolutional Neural Networks, Vision MLP architectures have demonstrated strong performance…
EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation
Suman Saha, Lukas Hoyer, Anton Obukhov +2
With autonomous industries on the rise, domain adaptation of the visual perception stack is an important research direction due to the cost savings promise. Much prior art was dedi…
Spatio-Temporal Action Detection Under Large Motion
Gurkirt Singh, Vasileios Choutas, Suman Saha +2
Current methods for spatiotemporal action tube detection often extend a bounding box proposal at a given keyframe into a 3D temporal cuboid and pool features from nearby frames. Ho…
Exploiting Instance-based Mixed Sampling via Auxiliary Source Domain Supervision for Domain-adaptive Action Detection
Yifan Lu, Gurkirt Singh, Suman Saha +1
We propose a novel domain adaptive action detection approach and a new adaptation protocol that leverages the recent advancements in image-level unsupervised domain adaptation (UDA…
Unsupervised Compound Domain Adaptation for Face Anti-Spoofing
Ankush Panwar, Pratyush Singh, Suman Saha +2
We address the problem of face anti-spoofing which aims to make the face verification systems robust in the real world settings. The context of detecting live vs. spoofed face imag…
Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation
Suman Saha, Anton Obukhov, Danda Pani Paudel +4
We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. Semantic segmentation and monocular d…
ROAD: The ROad event Awareness Dataset for Autonomous Driving
Gurkirt Singh, Stephen Akrigg, Manuele Di Maio +13
Humans drive in a holistic fashion which entails, in particular, understanding dynamic road events and their evolution. Injecting these capabilities in autonomous vehicles can thus…
Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation
Lukas Hoyer, Dengxin Dai, Yuhua Chen +3
Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a…
Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference
Menelaos Kanakis, David Bruggemann, Suman Saha +3
Multi-task networks are commonly utilized to alleviate the need for a large number of highly specialized single-task networks. However, two common challenges in developing multi-ta…
Two-Stream AMTnet for Action Detection
Suman Saha, Gurkirt Singh, Fabio Cuzzolin
In this paper, we propose Two-Stream AMTnet, which leverages recent advances in video-based action representation[1] and incremental action tube generation[2]. Majority of the pres…
Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing
Suman Saha, Wenhao Xu, Menelaos Kanakis +4
Nowadays, the increasingly growing number of mobile and computing devices has led to a demand for safer user authentication systems. Face anti-spoofing is a measure towards this di…
Predicting Action Tubes
Gurkirt Singh, Suman Saha, Fabio Cuzzolin
In this work, we present a method to predict an entire `action tube' (a set of temporally linked bounding boxes) in a trimmed video just by observing a smaller subset of it. Predic…
TraMNet - Transition Matrix Network for Efficient Action Tube Proposals
Gurkirt Singh, Suman Saha, Fabio Cuzzolin
Current state-of-the-art methods solve spatiotemporal action localisation by extending 2D anchors to 3D-cuboid proposals on stacks of frames, to generate sets of temporally connect…
Action Detection from a Robot-Car Perspective
Valentina Fontana, Gurkirt Singh, Stephen Akrigg +3
We present the new Road Event and Activity Detection (READ) dataset, designed and created from an autonomous vehicle perspective to take action detection challenges to autonomous d…
Unsupervised Deep Representations for Learning Audience Facial Behaviors
Suman Saha, Rajitha Navarathna, Leonhard Helminger +1
In this paper, we present an unsupervised learning approach for analyzing facial behavior based on a deep generative model combined with a convolutional neural network (CNN). We jo…
Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos
Suman Saha, Gurkirt Singh, Michael Sapienza +2
Current state-of-the-art human action recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame. In this work we address t…
AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture
Suman Saha, Gurkirt Singh, Fabio Cuzzolin
Dominant approaches to action detection can only provide sub-optimal solutions to the problem, as they rely on seeking frame-level detections, to later compose them into "action tu…
Incremental Tube Construction for Human Action Detection
Harkirat Singh Behl, Michael Sapienza, Gurkirt Singh +3
Current state-of-the-art action detection systems are tailored for offline batch-processing applications. However, for online applications like human-robot interaction, current sys…
Online Real-time Multiple Spatiotemporal Action Localisation and Prediction
Gurkirt Singh, Suman Saha, Michael Sapienza +2
We present a deep-learning framework for real-time multiple spatio-temporal (S/T) action localisation, classification and early prediction. Current state-of-the-art approaches work…
Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos
Suman Saha, Gurkirt Singh, Michael Sapienza +2
In this work, we propose an approach to the spatiotemporal localisation (detection) and classification of multiple concurrent actions within temporally untrimmed videos. Our framew…