Search Results for author:
Found 45 papers, 29 papers with code
Lifting Multi-View Detection and Tracking to the Bird's Eye View
Taking advantage of multi-view aggregation presents a promising solution to tackle challenges such as occlusion and missed detection in multi-object tracking and detection.
Ranked #1 on
Multiview Detection
on MultiviewX
Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perception
Low-cost, vision-centric 3D perception systems for autonomous driving have made significant progress in recent years, narrowing the gap to expensive LiDAR-based methods.
Ranked #1 on
3D Object Detection
on nuscenes Camera-Radar
EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View
Most current approaches in multi-view tracking perform the detection and tracking task in each view and use graph-based approaches to perform the association of the pedestrian across each view.
Ranked #2 on
Multi-Object Tracking
on MultiviewX
Do We Still Need Non-Maximum Suppression? Accurate Confidence Estimates and Implicit Duplication Modeling with IoU-Aware Calibration
Object detectors are at the heart of many semi- and fully autonomous decision systems and are poised to become even more indispensable.
Tackling Face Verification Edge Cases: In-Depth Analysis and Human-Machine Fusion Approach
Finally, we demonstrate that combining machine and human decisions can further improve the performance of state-of-the-art face verification systems on various benchmark datasets.
Explainable Model-Agnostic Similarity and Confidence in Face Verification
This work focuses on explanations for face recognition systems, vital for developers and operators.
Synthehicle: Multi-Vehicle Multi-Camera Tracking in Virtual Cities
Smart City applications such as intelligent traffic routing or accident prevention rely on computer vision methods for exact vehicle localization and tracking.
Ranked #1 on
Multi-Object Tracking
on Synthehicle
Octuplet Loss: Make Face Recognition Robust to Image Resolution
To address this problem, we propose a novel combination of the popular triplet loss to improve robustness against image resolution via fine-tuning of existing face recognition models.
Ranked #1 on
Face Recognition
on XQLFW
Wavelet Regularization Benefits Adversarial Training
Since adversarial vulnerability can be regarded as a high-frequency phenomenon, it is essential to regulate the adversarially-trained neural network models in the frequency domain.
Face Morphing: Fooling a Face Recognition System Is Simple!
State-of-the-art face recognition (FR) approaches have shown remarkable results in predicting whether two faces belong to the same identity, yielding accuracies between 92% and 100% depending on the difficulty of the protocol.
Towards a Deeper Understanding of Skeleton-based Gait Recognition
Gait recognition is a promising biometric with unique properties for identifying individuals from a long distance by their walking patterns.
The Box Size Confidence Bias Harms Your Object Detector
Recent work even suggests that detectors' confidence predictions are biased with respect to object size and position, but it is still unclear how this bias relates to the performance of the affected object detectors.
Cross-Quality LFW: A Database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments
Real-world face recognition applications often deal with suboptimal image quality or resolution due to different capturing conditions such as various subject-to-camera distances, poor camera settings, or motion blur.
Susceptibility to Image Resolution in Face Recognition and Trainings Strategies
In this work, we first analyze the impact of image resolutions on face verification performance with a state-of-the-art face recognition model.
Attention-based Partial Face Recognition
In this paper, we propose a novel approach to partial face recognition capable of recognizing faces with different occluded areas.
How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild
Successful active speaker detection requires a three-stage pipeline: (i) audio-visual encoding for all speakers in the clip, (ii) inter-speaker relation modeling between a reference speaker and the background speakers within each frame, and (iii) temporal modeling for the reference speaker.
Adversarial Joint Training with Self-Attention Mechanism for Robust End-to-End Speech Recognition
Inspired by the extensive applications of the generative adversarial networks (GANs) in speech enhancement and ASR tasks, we propose an adversarial joint training framework with the self-attention mechanism to boost the noise robustness of the ASR system.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognition
However, silhouette images can lose fine-grained spatial information, and most papers do not regard how to obtain these silhouettes in complex scenes.
Ranked #9 on
Multiview Gait Recognition
on CASIA-B
Lightweight Multi-Branch Network for Person Re-Identification
Person Re-Identification aims to retrieve person identities from images captured by multiple cameras or the same cameras in different time instances and locations.
Ranked #1 on
Person Re-Identification
on Market-1501
(mINP metric)
Lightweight End-to-End Speech Recognition from Raw Audio Data Using Sinc-Convolutions
For this, we propose Lightweight Sinc-Convolutions (LSC) that integrate Sinc-convolutions with depthwise convolutions as a low-parameter machine-learnable feature extraction for end-to-end ASR systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Driver Anomaly Detection: A Dataset and Contrastive Learning Approach
For this task, we introduce a new video-based benchmark, the Driver Anomaly Detection (DAD) dataset, which contains normal driving videos together with a set of anomalous actions in its training set.
Dissected 3D CNNs: Temporal Skip Connections for Efficient Online Video Processing
Convolutional Neural Networks with 3D kernels (3D-CNNs) currently achieve state-of-the-art results in video recognition tasks due to their supremacy in extracting spatiotemporal features within video frames.
MP3 Compression To Diminish Adversarial Noise in End-to-End Speech Recognition
The present work proposes MP3 compression as a means to decrease the impact of Adversarial Noise (AN) in audio samples transcribed by ASR systems.
Audio and Speech Processing Cryptography and Security Sound
CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition
In this work, we combine freely available corpora for German speech recognition, including yet unlabeled speech data, to a big dataset of over $1700$h of speech data.
Ranked #5 on
Speech Recognition
on TUDA
(using extra training data)
Speech Recognition
Audio and Speech Processing
Regularized Forward-Backward Decoder for Attention Models
Nowadays, attention models are one of the popular candidates for speech recognition.
A Multi-Task Comparator Framework for Kinship Verification
Approaches for kinship verification often rely on cosine distances between face identification features.
DriverMHG: A Multi-Modal Dataset for Dynamic Recognition of Driver Micro Hand Gestures and a Real-Time Recognition Framework
In this work, we propose an HCI system for dynamic recognition of driver micro hand gestures, which can have a crucial impact in automotive sector especially for safety related issues.
Deep Attention Based Semi-Supervised 2D-Pose Estimation for Surgical Instruments
To this end, a lightweight network architecture is introduced and mean teacher, virtual adversarial training and pseudo-labeling algorithms are evaluated on 2D-pose estimation for surgical instruments.
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
YOWO is a single-stage architecture with two branches to extract temporal and spatial information concurrently and predict bounding boxes and action probabilities directly from video clips in one evaluation.
Ranked #1 on
Action Recognition In Videos
on AVA v2.2
Small-Footprint Keyword Spotting on Raw Audio Data with Sinc-Convolutions
Keyword Spotting (KWS) enables speech-based user interaction on smart devices.
Comparative Analysis of CNN-based Spatiotemporal Reasoning in Videos
Understanding actions and gestures in video streams requires temporal reasoning of the spatial content from different time instants, i. e., spatiotemporal (ST) modeling.
Ranked #117 on
Action Recognition
on Something-Something V2
Real-Time Driver State Monitoring Using a CNN Based Spatio-Temporal Approach
Experiments show that our approach outperforms the state-of-the art results on the Distracted Driver Dataset (96. 31%), with an accuracy of 99. 10% for 10-class classification while providing real-time performance.
On Flow Profile Image for Video Representation
Video representation is a key challenge in many computer vision applications such as video classification, video captioning, and video surveillance.
Talking With Your Hands: Scaling Hand Gestures and Recognition With CNNs
The use of hand gestures provides a natural alternative to cumbersome interface devices for Human-Computer Interaction (HCI) systems.
Resource Efficient 3D Convolutional Neural Networks
Recently, convolutional neural networks with 3D kernels (3D CNNs) have been very popular in computer vision community as a result of their superior ability of extracting spatio-temporal features within video frames compared to 2D CNNs.
Ranked #2 on
Action Recognition In Videos
on UCF101
Real-time Hand Gesture Detection and Classification Using Convolutional Neural Networks
We evaluate our architecture on two publicly available datasets - EgoGesture and NVIDIA Dynamic Hand Gesture Datasets - which require temporal detection and classification of the performed hand gestures.
Ranked #1 on
Hand Gesture Recognition
on EgoGesture
Convolutional Neural Networks with Layer Reuse
In this paper, we propose a CNN architecture, Layer Reuse Network (LruNet), where the convolutional layers are used repeatedly without the need of introducing new layers to get a better performance.
Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification
To this end, tracklet re-identification is performed by utilizing a novel multi-stage deep network that can jointly reason about the visual appearance and spatio-temporal properties of a pair of tracklets, thereby providing a robust measure of affinity.
Robust Facial Landmark Detection via a Fully-Convolutional Local-Global Context Network
While fully-convolutional neural networks are very strong at modeling local features, they fail to aggregate global context due to their constrained receptive field.
Person Identification from Partial Gait Cycle Using Fully Convolutional Neural Network
In gait recognition, normally, gait feature such as Gait Energy Image (GEI) is extracted from one full gait cycle.
Motion Fused Frames: Data Level Fusion Strategy for Hand Gesture Recognition
Acquiring spatio-temporal states of an action is the most crucial step for action classification.
Ranked #1 on
Hand Gesture Recognition
on ChaLean test
A Deep Convolutional Neural Network for Background Subtraction
In this work, we present a novel background subtraction system that uses a deep Convolutional Neural Network (CNN) to perform the segmentation.
A Broadcast News Corpus for Evaluation and Tuning of German LVCSR Systems
Transcription of broadcast news is an interesting and challenging application for large-vocabulary continuous speech recognition (LVCSR).
Acoustic Gait-based Person Identification using Hidden Markov Models
The goal of the system is to analyse sounds emitted by walking persons (mostly the step sounds) and identify those persons.
Hypergraphs for Joint Multi-view Reconstruction and Multi-object Tracking
We generalize the network flow formulation for multiobject tracking to multi-camera setups.
