Search Results for author:
Found 148 papers, 89 papers with code
Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization
Open-Set Domain Generalization (OSDG) is a challenging task requiring models to accurately predict familiar categories while minimizing confidence for unknown categories to effectively reject them in unseen domains.
Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problems
3D visual grounding (3DVG) aims to locate objects in a 3D scene with natural language descriptions.
Muscles in Time: Learning to Understand Human Motion by Simulating Muscle Activations
In this work, we address this issue by establishing Muscles in Time (MinT), a large-scale synthetic muscle activation dataset.
Every Component Counts: Rethinking the Measure of Success for Medical Semantic Segmentation in Multi-Instance Segmentation Tasks
We present Connected-Component~(CC)-Metrics, a novel semantic segmentation evaluation protocol, targeted to align existing semantic segmentation metrics to a multi-instance detection scenario in which each connected component matters.
LIMIS: Towards Language-based Interactive Medical Image Segmentation
Within this work, we introduce LIMIS: The first purely language-based interactive medical image segmentation model.
Activity Recognition on Avatar-Anonymized Datasets with Masked Differential Privacy
Prevalent methods tackling this problem use differential privacy (DP) or obfuscation techniques to protect the privacy of individuals.
Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler
In this paper, we observe that an adaptive domain scheduler benefits more in OSDG compared with prefixed sequential and random domain schedulers.
Statewide Visual Geolocalization in the Wild
This work presents a method that is able to predict the geolocation of a street-view photo taken in the wild within a state-sized search region by matching against a database of aerial reference imagery.
@Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology
As Vision-Language Models (VLMs) advance, human-centered Assistive Technologies (ATs) for helping People with Visual Impairments (PVIs) are evolving into generalists, capable of performing multiple tasks simultaneously.
OneBEV: Using One Panoramic Image for Bird's-Eye-View Semantic Mapping
This work advances BEV semantic mapping in autonomous driving, paving the way for more advanced and reliable autonomous systems.
Data Diet: Can Trimming PET/CT Datasets Enhance Lesion Segmentation?
In this work, we describe our approach to compete in the autoPET3 datacentric track.
Comb, Prune, Distill: Towards Unified Pruning for Vision Model Compression
Extensive experiments demonstrate the generalizability of our framework, encompassing both convolutional neural network (CNN) and transformer models, as well as image classification and segmentation tasks.
Strike the Balance: On-the-Fly Uncertainty based User Interactions for Long-Term Video Object Segmentation
In this paper, we introduce a variant of video object segmentation (VOS) that bridges interactive and semi-automatic approaches, termed Lazy Video Object Segmentation (ziVOS).
Open Panoramic Segmentation
To tackle this problem, in this work, we define a new task termed Open Panoramic Segmentation (OPS), where models are trained with FoV-restricted pinhole images in the source domain in an open-vocabulary setting while evaluated with FoV-open panoramic images in the target domain, enabling the zero-shot open panoramic semantic segmentation ability of models.
Occlusion-Aware Seamless Segmentation
Our method achieves state-of-the-art performance on the BlendPASS dataset, reaching a remarkable mAPQ of 26. 58% and mIoU of 43. 66%.
Referring Atomic Video Action Recognition
Since these existing methods underperform on RAVAR, we introduce RefAtomNet -- a novel cross-stream attention-driven method specialized for the unique challenges of RAVAR: the need to interpret a textual referring expression for the targeted individual, utilize this reference to guide the spatial localization and harvest the prediction of the atomic actions for the referring person.
SciEx: Benchmarking Large Language Models on Scientific Exams with Human Expert Grading and Automatic Grading
We evaluate the performance of various state-of-the-art LLMs on our new benchmark.
Alt4Blind: A User Interface to Simplify Charts Alt-Text Creation
We address this challenge by retrieving high-quality alt-texts from similar chart images, serving as a reference for the user when creating alt-texts.
ChartFormer: A Large Vision Language Model for Converting Chart Images into Tactile Accessible SVGs
Visualizations, such as charts, are crucial for interpreting complex data.
ACCSAMS: Automatic Conversion of Exam Documents to Accessible Learning Material for Blind and Visually Impaired
Exam documents are essential educational materials for exam preparation.
AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks
Chart summarization is a crucial task for blind and visually impaired individuals as it is their primary means of accessing and interpreting graphical data.
Rethinking Annotator Simulation: Realistic Evaluation of Whole-Body PET Lesion Interactive Segmentation Methods
In an initial user study involving four annotators, we assess existing robot users using our proposed metrics and find that robot users significantly deviate in performance and annotation behavior compared to real annotators.
RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
To address this, we are the first to introduce a robustness benchmark for DLA models, which includes 450K document images of three datasets.
Skeleton-Based Human Action Recognition with Noisy Labels
In this study, we bridge this gap by implementing a framework that augments well-established skeleton-based human action recognition methods with label-denoising strategies from various research areas to serve as the initial benchmark.
EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Driving
This paper introduces the task of Auditory Referring Multi-Object Tracking (AR-MOT), which dynamically tracks specific objects in a video sequence based on audio expressions and appears as a challenging problem in autonomous driving.
Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation
Integrating information from multiple modalities enhances the robustness of scene perception systems in autonomous vehicles, providing a more comprehensive and reliable sensory framework.
C-BEV: Contrastive Bird's Eye View Training for Cross-View Image Retrieval and 3-DoF Pose Estimation
To find the geolocation of a street-view image, cross-view geolocalization (CVGL) methods typically perform image retrieval on a database of georeferenced aerial images and determine the location from the visually most similar match.
Navigating Open Set Scenarios for Skeleton-based Action Recognition
In real-world scenarios, human actions often fall outside the distribution of training data, making it crucial for models to recognize known actions and reject unknown ones.
Sliding Window FastEdit: A Framework for Lesion Annotation in Whole-body PET Images
Deep learning has revolutionized the accurate segmentation of diseases in medical imaging.
Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy
Interactive segmentation is a crucial research area in medical image analysis aiming to boost the efficiency of costly annotations by incorporating human feedback.
Quantized Distillation: Optimizing Driver Activity Recognition Models for Resource-Constrained Environments
The framework enhances 3D MobileNet, a neural architecture optimized for speed in video classification, by incorporating knowledge distillation and model quantization to balance model accuracy and computational efficiency.
CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementarity
Roadside camera-driven 3D object detection is a crucial task in intelligent transportation systems, which extends the perception range beyond the limitations of vision-centric vehicles and enhances road safety.
Ranked #2 on
3D Object Detection
on Rope3D
Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision
These works overlooked the differences in performance among modalities, which led to the propagation of erroneous knowledge between modalities while only three fundamental modalities, i. e., joints, bones, and motions are used, hence no additional modalities are explored.
AutoPET Challenge 2023: Sliding Window-based Optimization of U-Net
Tumor segmentation in medical imaging is crucial and relies on precise delineation.
Exploring Self-Supervised Skeleton-Based Human Action Recognition under Occlusions
To empower models with the capacity to address occlusion, we propose a simple and effective method.
MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Vision
For the medical domain, we present a large collection of anatomical shapes (e. g., bones, organs, vessels) and 3D models of surgical instrument, called MedShapeNet, created to facilitate the translation of data-driven vision algorithms to medical applications and to adapt SOTA vision algorithms to medical problems.
Towards Privacy-Supporting Fall Detection via Deep Unsupervised RGB2Depth Adaptation
In this paper, we introduce a privacy-supporting solution that makes the RGB-trained model applicable in depth domain and utilizes depth data at test time for fall detection.
On Transferability of Driver Observation Models from Simulated to Real Environments in Autonomous Cars
For driver observation frameworks, clean datasets collected in controlled simulated environments often serve as the initial training ground.
OAFuser: Towards Omni-Aperture Fusion for Light Field Semantic Segmentation
To simultaneously streamline the redundant information from the light field cameras and avoid feature loss during network propagation, we present a simple yet very effective Sub-Aperture Fusion Module (SAFM).
Towards Unifying Anatomy Segmentation: Automated Generation of a Full-body CT Dataset via Knowledge Aggregation and Anatomical Guidelines
We examine its plausibility and usefulness using three complementary checks: Human expert evaluation which approved the dataset, a Deep Learning usefulness benchmark on the BTCV dataset in which we achieve 85% dice score without using its training dataset, and medical validity checks.
Tightly-Coupled LiDAR-Visual SLAM Based on Geometric Features for Mobile Agents
On the other hand, the entire line segment detected by the visual subsystem overcomes the limitation of the LiDAR subsystem, which can only perform the local calculation for geometric features.
Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments
Grounded Situation Recognition (GSR) is capable of recognizing and interpreting visual scenes in a contextually intuitive way, yielding salient activities (verbs) and the involved entities (roles) depicted in images.
Line Graphics Digitization: A Step Towards Full Automation
The digitization of documents allows for wider accessibility and reproducibility.
Accurate Fine-Grained Segmentation of Human Anatomy in Radiographs via Volumetric Pseudo-Labeling
Results: Our resulting segmentation models demonstrated remarkable performance on CXR, with a high average model-annotator agreement between two radiologists with mIoU scores of 0. 93 and 0. 85 for frontal and lateral anatomy, while inter-annotator agreement remained at 0. 95 and 0. 83 mIoU.
READMem: Robust Embedding Association for a Diverse Memory in Unconstrained Video Object Segmentation
We present READMem (Robust Embedding Association for a Diverse Memory), a modular framework for semi-automatic video object segmentation (sVOS) methods designed to handle unconstrained videos.
Semantic Segmentation
Semi-Supervised Video Object Segmentation
+1
Exploring Few-Shot Adaptation for Activity Recognition on Diverse Domains
In this work, we focus on Few-Shot Domain Adaptation for Activity Recognition (FSDA-AR), which leverages a very small amount of labeled target videos to achieve effective adaptation.
FishDreamer: Towards Fisheye Semantic Completion via Unified Image Outpainting and Segmentation
This paper raises the new task of Fisheye Semantic Completion (FSC), where dense texture, structure, and semantics of a fisheye image are inferred even beyond the sensor field-of-view (FoV).
360BEV: Panoramic Semantic Mapping for Indoor Bird's-Eye View
Seeing only a tiny part of the whole is not knowing the full circumstance.
Guiding the Guidance: A Comparative Analysis of User Guidance Signals for Interactive Segmentation of Volumetric Images
To address this, we conduct a comparative study of existing guidance signals by training interactive models with different signals and parameter settings to identify crucial parameters for the model's design.
Mirror U-Net: Marrying Multimodal Fission with Multi-task Learning for Semantic Segmentation in Medical Imaging
Positron Emission Tomography (PET) and Computer Tomography (CT) are routinely used together to detect tumors.
Towards Activated Muscle Group Estimation in the Wild
To this intent, we provide the MuscleMap dataset featuring >15K video clips with 135 different activities and 20 labeled muscle groups.
Delivering Arbitrary-Modal Semantic Segmentation
To make this possible, we present the arbitrary cross-modal segmentation model CMNeXt.
Ranked #1 on
Semantic Segmentation
on Porto
MateRobot: Material Recognition in Wearable Robotics for People with Visual Impairments
People with Visual Impairments (PVI) typically recognize objects through haptic perception.
Multimodal Interactive Lung Lesion Segmentation: A Framework for Annotating PET/CT Images based on Physiological and Anatomical Cues
Recently, deep learning enabled the accurate segmentation of various diseases in medical imaging.
Decoupled Semantic Prototypes Enable Learning From Diverse Annotation Types for Semi-Weakly Segmentation in Expert-Driven Domains
A vast amount of images and pixel-wise annotations allowed our community to build scalable segmentation solutions for natural domains.
Uncertainty-aware Vision-based Metric Cross-view Geolocalization
This paper proposes a novel method for vision-based metric cross-view geolocalization (CVGL) that matches the camera images captured from a ground-based vehicle with an aerial image to determine the vehicle's geo-pose.
Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation
Although human action anticipation is a task which is inherently multi-modal, state-of-the-art methods on well known action anticipation datasets leverage this data by applying ensemble methods and averaging scores of unimodal anticipation networks.
Ranked #3 on
Action Anticipation
on EPIC-KITCHENS-100 (test)
Detailed Annotations of Chest X-Rays via CT Projection for Report Understanding
To exploit anatomical structures in this scenario, we present a sophisticated automatic pipeline to gather and integrate human bodily structures from computed tomography datasets, which we incorporate in our PAXRay: A Projected dataset for the segmentation of Anatomical structures in X-Ray data.
AutoPET Challenge: Combining nn-Unet with Swin UNETR Augmented by Maximum Intensity Projection Classifier
Tumor volume and changes in tumor characteristics over time are important biomarkers for cancer therapy.
ModSelect: Automatic Modality Selection for Synthetic-to-Real Domain Generalization
Modality selection is an important step when designing multimodal systems, especially in the case of cross-domain activity recognition as certain modalities are more robust to domain shift than others.
Multimodal Generation of Novel Action Appearances for Synthetic-to-Real Recognition of Activities of Daily Living
We tackle this challenge and introduce an activity domain generation framework which creates novel ADL appearances (novel domains) from different existing activity modalities (source domains) inferred from video training data.
Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation
In this paper, we address panoramic semantic segmentation which is under-explored due to two critical challenges: (1) image distortions and object deformations on panoramas; (2) lack of semantic annotations in the 360{\deg} imagery.
Ranked #1 on
Semantic Segmentation
on SynPASS
Trans4Map: Revisiting Holistic Bird's-Eye-View Mapping from Egocentric Images to Allocentric Semantics with Vision Transformers
Humans have an innate ability to sense their surroundings, as they can extract the spatial representation from the egocentric perception and form an allocentric semantic map via spatial transformation and memory updating.
Multi-modal Depression Estimation based on Sub-attentional Fusion
Failure to timely diagnose and effectively treat depression leads to over 280 million people suffering from this psychological disorder worldwide.
Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learning
In order to overcome the lack of annotated panoramic images, we propose a framework which allows model training on standard pinhole images and transfers the learned features to the panoramic domain in a cost-minimizing way.
Breaking with Fixed Set Pathology Recognition through Report-Guided Contrastive Training
We show that despite using unstructured medical report supervision, we perform on par with direct label supervision through a sophisticated inference setting.
Ranked #2 on
Thoracic Disease Classification
on ChestX-ray14
Towards Automatic Parsing of Structured Visual Content through the Use of Synthetic Data
In this work, we propose a synthetic dataset, containing SVCs in the form of images as well as ground truths.
Is my Driver Observation Model Overconfident? Input-guided Calibration Networks for Reliable and Interpretable Confidence Estimates
In this work, we for the first time examine how well the confidence values of modern driver observation models indeed match the probability of the correct outcome and show that raw neural network-based approaches tend to significantly overestimate their prediction quality.
A Comparative Analysis of Decision-Level Fusion for Multimodal Driver Behaviour Understanding
Visual recognition inside the vehicle cabin leads to safer driving and more intuitive human-vehicle interaction but such systems face substantial obstacles as they need to capture different granularities of driver behaviour while dealing with highly limited body visibility and changing illumination.
Indoor Navigation Assistance for Visually Impaired People via Dynamic SLAM and Panoptic Segmentation with an RGB-D Sensor
Then, poses and speed of tracked dynamic objects can be estimated, which are passed to the users through acoustic feedback.
Hierarchical Nearest Neighbor Graph Embedding for Efficient Dimensionality Reduction
Dimensionality reduction is crucial both for visualization and preprocessing high dimensional data for machine learning.
Ranked #3 on
Data Augmentation
on GA1457
Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-Learning
Autonomous vehicles utilize urban scene segmentation to understand the real world like a human and react accordingly.
Ranked #1 on
Semantic Segmentation
on DADA-seg
(using extra training data)
MatchFormer: Interleaving Attention in Transformers for Feature Matching
While detector-based methods coupled with feature descriptors struggle in low-texture scenes, CNN-based methods with a sequential extract-to-match pipeline, fail to make use of the matching capacity of the encoder and tend to overburden the decoder for matching.
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
Pixel-wise semantic segmentation of RGB images can be advanced by exploiting complementary features from the supplementary modality (X-modality).
Ranked #1 on
Image Manipulation Localization
on CocoGlide
Continuous Self-Localization on Aerial Images Using Visual and Lidar Sensors
Our method is the first to utilize on-board cameras in an end-to-end differentiable model for metric self-localization on unseen orthophotos.
Revisiting Click-based Interactive Video Object Segmentation
While current methods for interactive Video Object Segmentation (iVOS) rely on scribble-based interactions to generate precise object masks, we propose a Click-based interactive Video Object Segmentation (CiVOS) framework to simplify the required user workload as much as possible.
TransDARC: Transformer-based Driver Activity Recognition with Latent Space Feature Calibration
This module operates in the latent feature-space enriching and diversifying the training set at feature-level in order to improve generalization to novel data appearances, (e. g., sensor changes) and general feature quality.
Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation
To get around this domain difference and bring together semantic annotations from pinhole- and 360-degree surround-visuals, we propose to learn object deformations and panoramic image distortions in the Deformable Patch Embedding (DPE) and Deformable MLP (DMLP) components which blend into our Transformer for PAnoramic Semantic Segmentation (Trans4PASS) model.
Ranked #2 on
Semantic Segmentation
on SynPASS
TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation
Furthermore, we introduce two optimization modules to enhance the patch embedding distillation from different perspectives: (1) Global-Local Context Mixer (GL-Mixer) extracts both global and local information of a representative embedding; (2) Embedding Assistant (EA) acts as an embedding method to seamlessly bridge teacher and student models with the teacher's number of channels.
Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions
Yet, the research of data-scarce recognition from skeleton sequences, such as one-shot action recognition, does not explicitly consider occlusions despite their everyday pervasiveness.
Ranked #1 on
Action Classification
on Toyota Smarthome dataset
(Accuracy metric)
Should I take a walk? Estimating Energy Expenditure from Video Data
To study this underresearched task, we introduce Vid2Burn -- an omni-source benchmark for estimating caloric expenditure from video data featuring both, high- and low-intensity activities for which we derive energy expenditure annotations based on models established in medical literature.
Exploring Event-driven Dynamic Context for Accident Scene Segmentation
Moreover, in order to evaluate the segmentation performance in traffic accidents, we provide a pixel-wise annotated accident dataset, namely DADA-seg, which contains a variety of critical scenarios from traffic accidents.
Ranked #3 on
Semantic Segmentation
on DADA-seg
(using extra training data)
Reference-guided Pseudo-Label Generation for Medical Semantic Segmentation
Following this thought, we use a small number of labeled images as reference material and match pixels in an unlabeled image to the semantics of the best fitting pixel in a reference set.
Affect-DML: Context-Aware One-Shot Recognition of Human Affect using Deep Metric Learning
Human affect recognition is a well-established research area with numerous applications, e. g., in psychological care, but existing methods assume that all emotions-of-interest are given a priori as annotated training examples.
Certainty Volume Prediction for Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) deals with the problem of classifying unlabeled target domain data while labeled data is only available for a different source domain.
UBR$^2$S: Uncertainty-Based Resampling and Reweighting Strategy for Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) deals with the adaptation process of a model to an unlabeled target domain while annotated data is only available for a given source domain.
Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation
We look at this problem from the perspective of domain adaptation and bring panoramic semantic segmentation to a setting, where labelled training data originates from a different distribution of conventional pinhole camera images.
Ranked #7 on
Semantic Segmentation
on DensePASS
(using extra training data)
Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance
In this paper, we build a wearable system with a novel dual-head Transformer for Transparency (Trans4Trans) perception model, which can segment general- and transparent objects.
Ranked #2 on
Semantic Segmentation
on DADA-seg
(using extra training data)
Flying Guide Dog: Walkable Path Discovery for the Visually Impaired Utilizing Drones and Transformer-based Semantic Segmentation
By recognizing the color of pedestrian traffic lights, our prototype can help the user to cross a street safely.
DensePASS: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation with Attention-Augmented Context Exchange
First, we formalize the task of unsupervised domain adaptation for panoramic semantic segmentation, where a network trained on labelled examples from the source domain of pinhole camera data is deployed in a different target domain of panoramic images, for which no labels are available.
Let's Play for Action: Recognizing Activities of Daily Living by Learning from Life Simulation Video Games
Recognizing Activities of Daily Living (ADL) is a vital process for intelligent assistive robots, but collecting large annotated datasets requires time-consuming temporal labeling and raises privacy concerns, e. g., if the data is collected in a real household.
Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World
Common fully glazed facades and transparent objects present architectural barriers and impede the mobility of people with low vision or blindness, for instance, a path detected behind a glass door is inaccessible unless it is correctly perceived and reacted.
Ranked #1 on
Semantic Segmentation
on Trans10K
HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor
To tackle these issues, we propose HIDA, a lightweight assistive system based on 3D point cloud instance segmentation with a solid-state LiDAR sensor, for holistic indoor detection and avoidance.
Ranked #19 on
3D Instance Segmentation
on ScanNet(v2)
MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understanding
At the heart of all automated driving systems is the ability to sense the surroundings, e. g., through semantic segmentation of LiDAR sequences, which experienced a remarkable progress due to the release of large datasets such as SemanticKITTI and nuScenes-LidarSeg.
Pose2Drone: A Skeleton-Pose-based Framework for Human-Drone Interaction
Our framework provides the functionality to control the movement of the drone with simple arm gestures and to follow the user while keeping a safe distance.
Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation
Pixel-wise segmentation is one of the most data and annotation hungry tasks in our field.
Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation
Action segmentation refers to inferring boundaries of semantically consistent visual concepts in videos and is an important requirement for many video understanding tasks.
Ranked #1 on
Action Segmentation
on MPII Cooking 2 Dataset
Capturing Omni-Range Context for Omnidirectional Segmentation
Convolutional Networks (ConvNets) excel at semantic segmentation and have become a vital component for perception in autonomous driving.
Ranked #10 on
Semantic Segmentation
on DensePASS
(using extra training data)
Perception Framework through Real-Time Semantic Segmentation and Scene Recognition on a Wearable System for the Visually Impaired
As the scene information, including objectness and scene type, are important for people with visual impairment, in this work we present a multi-task efficient perception system for the scene parsing and recognition tasks.
Panoptic Lintention Network: Towards Efficient Navigational Perception for the Visually Impaired
Based on Lintention, we then devise a novel panoptic segmentation model which we term Panoptic Lintention Net.
Panoramic Panoptic Segmentation: Towards Complete Surrounding Understanding via Unsupervised Contrastive Learning
In order to overcome the lack of annotated panoramic images, we propose a framework which allows model training on standard pinhole images and transfers the learned features to a different domain.
DR-TANet: Dynamic Receptive Temporal Attention Network for Street Scene Change Detection
Street scene change detection continues to capture researchers' interests in the computer vision community.
Prediction of low-keV monochromatic images from polyenergetic CT scans for improved automatic detection of pulmonary embolism
Detector-based spectral computed tomography is a recent dual-energy CT (DECT) technology that offers the possibility of obtaining spectral information.
Adaptiope: A Modern Benchmark for Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) deals with the adaptation process of a given source domain with labeled training data to a target domain for which only unannotated data is available.
Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and the CARING Models
While temperature scaling alone drastically improves the reliability of the confidence values, our CARING method consistently leads to the best uncertainty estimates in all benchmark settings.
Vi2CLR: Video and Image for Visual Contrastive Learning of Representation
In this paper, we introduce a novel self-supervised visual representation learning method which understands both images and videos in a joint learning fashion.
Multi-Task Learning for Calorie Prediction on a Novel Large-Scale Recipe Dataset Enriched with Nutritional Information
Our experiments demonstrate clear benefits of multi-task learning for calorie estimation, surpassing the single-task calorie regression by 9. 9%.
Self-Guided Multiple Instance Learning for Weakly Supervised Disease Classification and Localization in Chest Radiographs
In this paper, we address the problem of weakly supervised identification and localization of abnormalities in chest radiographs.
Unsupervised Domain Adaptation by Uncertain Feature Alignment
Unsupervised domain adaptation (UDA) deals with the adaptation of models from a given source domain with labeled data to an unlabeled target domain.
ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data
Ensuring the safety of all traffic participants is a prerequisite for bringing intelligent vehicles closer to practical applications.
Ranked #6 on
Semantic Segmentation
on KITTI-360
Anchor-free Small-scale Multispectral Pedestrian Detection
In this way, we can both simplify the network architecture and achieve higher detection performance, especially for pedestrians under occlusion or at low object resolution.
Can we cover navigational perception needs of the visually impaired by panoptic segmentation?
Navigational perception for visually impaired people has been substantially promoted by both classic and deep learning based segmentation methods.
Deep Multimodal Feature Encoding for Video Ordering
True understanding of videos comes from a joint analysis of all its modalities: the video frames, the audio track, and any accompanying text such as closed captions.
Clustering based Contrastive Learning for Improving Face Representations
We demonstrate our method on the challenging task of learning representations for video face clustering.
DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing
Semantically interpreting the traffic scene is crucial for autonomous transportation and robotics systems.
Ranked #35 on
Semantic Segmentation
on DensePASS
Content and Colour Distillation for Learning Image Translations with the Spatial Profile Loss
In this paper, we propose a novel method of computing the loss directly between the source and target images that enable proper distillation of shape/content and colour/style.
DynamoNet: Dynamic Action and Motion Network
With these overall objectives, to this end, we introduce a novel unified spatio-temporal 3D-CNN architecture (DynamoNet) that jointly optimizes the video classification and learning motion representation by predicting future frames as a multi-task learning problem.
Large Scale Holistic Video Understanding
HVU is organized hierarchically in a semantic taxonomy that focuses on multi-label and multi-task video understanding as a comprehensive problem that encompasses the recognition of multiple semantic aspects in the dynamic scene.
Ranked #13 on
Action Recognition
on UCF101
Self-Supervised Learning of Face Representations for Video Face Clustering
In this paper, we address video face clustering using unsupervised methods.
Efficient Parameter-free Clustering Using First Neighbor Relations
We present a new clustering method in the form of a single clustering equation that is able to directly discover groupings in the data.
Can Image Enhancement be Beneficial to Find Smoke Images in Laparoscopic Surgery?
For feature extraction, we use statistical features based on bivariate histogram distribution of gradient magnitude~(GM) and Laplacian of Gaussian~(LoG).
Informed Democracy: Voting-based Novelty Detection for Action Recognition
While it is common in activity recognition to assume a closed-set setting, i. e. test samples are always of training categories, this assumption is impractical in a real-world scenario.
Taming the Cross Entropy Loss
We present the Tamed Cross Entropy (TCE) loss function, a robust derivative of the standard Cross Entropy (CE) loss used in deep learning for classification tasks.
3D Vehicle Trajectory Reconstruction in Monocular Video Data Using Environment Structure Constraints
We apply Structure from Motion techniques to vehicle and background images to determine for each frame camera poses relative to vehicle instances and background structures.
Stereo 3D Object Trajectory Reconstruction
We compute the object trajectory by combining object and background camera pose information.
Classification-Driven Dynamic Image Enhancement
In this paper, we are interested in learning CNNs that can emulate image enhancement and restoration, but with the overall goal to improve image classification and not necessarily human perception.
A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking
In contrast to the recent direction of explicitly modeling body parts or correcting for misalignment based on these, we show that a rather straightforward inclusion of acquired camera view and/or the detected joint locations into a convolutional neural network helps to learn a very effective representation.
Ranked #17 on
Person Re-Identification
on MARS
Weakly Supervised Object Discovery by Generative Adversarial & Ranking Networks
We approach GANs with a novel training method and learning objective, to discover multiple object instances for three cases: 1) synthesizing a picture of a specific object within a cluttered scene; 2) localizing different categories in images for weakly supervised object detection; and 3) improving object discov- ery in object detection pipelines.
Ranked #2 on
Weakly Supervised Object Detection
on COCO test-dev
3D Trajectory Reconstruction of Dynamic Objects Using Planarity Constraints
We apply Structure from Motion techniques to object and background images to determine for each frame camera poses relative to object instances and background structures.