Search Results for author:
Found 22 papers, 10 papers with code
Online Real-time Multiple Spatiotemporal Action Localisation and Prediction
To the best of our knowledge, ours is the first real-time (up to 40fps) system able to perform online S/T action localisation and early action prediction on the untrimmed videos of UCF101-24.
Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation
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 highly labor-intensive process.
Ranked #4 on
Semi-Supervised Semantic Segmentation
on Cityscapes 100 samples labeled
(using extra training data)
ROAD: The ROad event Awareness Dataset for Autonomous Driving
We also report the performance on the ROAD tasks of Slowfast and YOLOv5 detectors, as well as that of the winners of the ICCV2021 ROAD challenge, which highlight the challenges faced by situation awareness in autonomous driving.
Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation
Specifically, we show that: (1) our approach improves performance on all tasks when they are complementary and mutually dependent; (2) the CTRL helps to improve both semantic segmentation and depth estimation tasks performance in the challenging UDA setting; (3) the proposed ISL training scheme further improves the semantic segmentation performance.
Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference
First, enabling the model to be inherently incremental, continuously incorporating information from new tasks without forgetting the previously learned ones (incremental learning).
EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation
EDAPS significantly improves the state-of-the-art performance for panoptic segmentation UDA by a large margin of 20% on SYNTHIA-to-Cityscapes and even 72% on the more challenging SYNTHIA-to-Mapillary Vistas.
Ranked #1 on
Domain Adaptation
on Panoptic SYNTHIA-to-Mapillary
Exploiting Instance-based Mixed Sampling via Auxiliary Source Domain Supervision for Domain-adaptive Action Detection
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) techniques and handle vagaries of instance-level video data.
Incremental Tube Construction for Human Action Detection
In this work, we introduce a real-time and online joint-labelling and association algorithm for action detection that can incrementally construct space-time action tubes on the most challenging action videos in which different action categories occur concurrently.
TraMNet - Transition Matrix Network for Efficient Action Tube Proposals
At training time, transitions are specific to cell locations of the feature maps, so that a sparse (efficient) transition matrix is used to train the network.
Two-Stream AMTnet for Action Detection
This is achieved by augmenting the previous Action Micro-Tube (AMTnet) action detection framework in three distinct ways: by adding a parallel motion stIn this paper, we propose a new deep neural network architecture for online action detection, termed ream to the original appearance one in AMTnet; (2) in opposition to state-of-the-art action detectors which train appearance and motion streams separately, and use a test time late fusion scheme to fuse RGB and flow cues, by jointly training both streams in an end-to-end fashion and merging RGB and optical flow features at training time; (3) by introducing an online action tube generation algorithm which works at video-level, and in real-time (when exploiting only appearance features).
Unsupervised Deep Representations for Learning Audience Facial Behaviors
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).
Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos
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.
AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture
As such, our 3D-RPN net is able to effectively encode the temporal aspect of actions by purely exploiting appearance, as opposed to methods which heavily rely on expensive flow maps.
Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos
In stage 2, the appearance network detections are boosted by combining them with the motion detection scores, in proportion to their respective spatial overlap.
Action Detection from a Robot-Car Perspective
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 driving.
Predicting Action Tubes
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.
Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing
Face anti-spoofing is a measure towards this direction for bio-metric user authentication, and in particular face recognition, that tries to prevent spoof attacks.
Unsupervised Compound Domain Adaptation for Face Anti-Spoofing
The proposed method successfully adapts to the compound target domain consisting multiple new spoof types.
Spatio-Temporal Action Detection Under Large Motion
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.
CS-Mixer: A Cross-Scale Vision MLP Model with Spatial-Channel Mixing
Despite their simpler information fusion designs compared with Vision Transformers and Convolutional Neural Networks, Vision MLP architectures have demonstrated strong performance and high data efficiency in recent research.
Three Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding
A common formulation to tackle 3D visual grounding is grounding-by-detection, where localization is done via bounding boxes.
Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentation
A key challenge in panoptic UDA is reducing the domain gap between a labeled source and an unlabeled target domain while harmonizing the subtasks of semantic and instance segmentation to limit catastrophic interference.
