Search Results for author:
Found 106 papers, 67 papers with code
Source-Free Domain Adaptation for YOLO Object Detection
Source-free domain adaptation (SFDA) is a challenging problem in object detection, where a pre-trained source model is adapted to a new target domain without using any source domain data for privacy and efficiency reasons.
Multi Teacher Privileged Knowledge Distillation for Multimodal Expression Recognition
However, PKD methods based on structural similarity are primarily confined to learning from a single joint teacher representation, which limits their robustness, accuracy, and ability to learn from diverse multimodal sources.
Textualized and Feature-based Models for Compound Multimodal Emotion Recognition in the Wild
Our results indicate that multimodal textualization provides lower accuracy than feature-based models on C-EXPR-DB, where text transcripts are captured in the wild.
Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos
Our TrCAM-V method allows training a localization network by sampling pseudo-pixels on the fly from these regions.
SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution
Given the new SR-CACO-2 dataset, we also provide benchmarking results for 15 state-of-the-art methods that are representative of the main SISR families.
MiPa: Mixed Patch Infrared-Visible Modality Agnostic Object Detection
Multimodal learning is a common way to leverage these modalities, where multiple modality-specific encoders and a fusion module are used to improve performance.
Ranked #1 on
Object Detection
on FLIR
Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histology
A WSOL model initially trained on some labeled source image data can be adapted using unlabeled target data in cases of significant domain shifts caused by variations in staining, scanners, and cancer type.
A Realistic Protocol for Evaluation of Weakly Supervised Object Localization
These bboxes are also employed to estimate the threshold from LOC maps, circumventing the need for test-set bbox annotations.
Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge
This paper focuses on adapting a large object detection model trained on RGB images to new data extracted from IR images with a substantial modality shift.
Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identification
In particular, our method minimizes the cross-modal gap by identifying and aligning shared prototypes that capture key discriminative features across modalities, then uses multiple bridging steps based on this information to enhance the feature representation.
Joint Multimodal Transformer for Emotion Recognition in the Wild
Multimodal emotion recognition (MMER) systems typically outperform unimodal systems by leveraging the inter- and intra-modal relationships between, e. g., visual, textual, physiological, and auditory modalities.
Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors
Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains.
Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues
During training, this \au codebook is used, along with the input image expression label, and facial landmarks, to construct a \au heatmap that indicates the most discriminative image regions of interest w. r. t the facial expression.
Facial Expression Recognition
Facial Expression Recognition (FER)
Distilling Privileged Multimodal Information for Expression Recognition using Optimal Transport
Results show that our proposed method can outperform state-of-the-art privileged KD methods on these problems.
SeTformer is What You Need for Vision and Language
Kernel methods are employed to simplify computations by approximating softmax but often lead to performance drops compared to softmax attention.
Pain Analysis using Adaptive Hierarchical Spatiotemporal Dynamic Imaging
These representations are optimized for two tasks: estimating pain intensity and differentiating between genuine and simulated pain expressions.
Subject-Based Domain Adaptation for Facial Expression Recognition
It efficiently leverages information from multiple source subjects (labeled source domain data) to adapt a deep FER model to a single target individual (unlabeled target domain data).
Facial Expression Recognition
Facial Expression Recognition (FER)
+2
Evaluating Supervision Levels Trade-Offs for Infrared-Based People Counting
Object detection models are commonly used for people counting (and localization) in many applications but require a dataset with costly bounding box annotations for training.
Domain Generalization by Rejecting Extreme Augmentations
However, this holds for standard in-domain settings, in which the training and test data follow the same distribution.
DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization
Subsequently, these proposals are used as pseudo-labels to train our new transformer-based WSOL model designed to perform classification and localization tasks.
HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information
This model produces a new image representation that enhances objects of interest in the scene and greatly improves detection performance.
Multi-Source Domain Adaptation for Object Detection with Prototype-based Mean-teacher
Given the use of prototypes, the number of parameters required for our PMT method does not increase significantly with the number of source domains, thus reducing memory issues and possible overfitting.
Multi-Source Unsupervised Domain Adaptation
object-detection
+2
Density Crop-guided Semi-supervised Object Detection in Aerial Images
One of the important bottlenecks in training modern object detectors is the need for labeled images where bounding box annotations have to be produced for each object present in the image.
Ranked #1 on
Object Detection
on VisDrone - 10% labeled data
Adaptive Generation of Privileged Intermediate Information for Visible-Infrared Person Re-Identification
In this paper, the Adaptive Generation of Privileged Intermediate Information training approach is introduced to adapt and generate a virtual domain that bridges discriminant information between the V and I modalities.
Image Completion via Dual-path Cooperative Filtering
Given the recent advances with image-generating algorithms, deep image completion methods have made significant progress.
Fusion for Visual-Infrared Person ReID in Real-World Surveillance Using Corrupted Multimodal Data
For realistic evaluation of multimodal (and cross-modal) V-I person ReID models, we propose new challenging corrupted datasets for scenarios where V and I cameras are co-located (CL) and not co-located (NCL).
Recursive Joint Attention for Audio-Visual Fusion in Regression based Emotion Recognition
In video-based emotion recognition (ER), it is important to effectively leverage the complementary relationship among audio (A) and visual (V) modalities, while retaining the intra-modal characteristics of individual modalities.
CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos
This paper proposes a novel CAM method for WSVOL that exploits spatiotemporal information in activation maps during training without constraining an object's position.
Cascaded Zoom-in Detector for High Resolution Aerial Images
Detecting objects in aerial images is challenging because they are typically composed of crowded small objects distributed non-uniformly over high-resolution images.
Ranked #2 on
Object Detection
on VisDrone-DET2019
Re-basin via implicit Sinkhorn differentiation
The recent emergence of new algorithms for permuting models into functionally equivalent regions of the solution space has shed some light on the complexity of error surfaces, and some promising properties like mode connectivity.
Multimodal Data Augmentation for Visual-Infrared Person ReID with Corrupted Data
Several deep learning models have been proposed for visible-infrared (V-I) person ReID to recognize individuals from images captured using RGB and IR cameras.
Camera Alignment and Weighted Contrastive Learning for Domain Adaptation in Video Person ReID
In this scenario, the ReID model must adapt to a complex target domain defined by a network of diverse video cameras based on tracklet information.
Privacy-Preserving Person Detection Using Low-Resolution Infrared Cameras
In intelligent building management, knowing the number of people and their location in a room are important for better control of its illumination, ventilation, and heating with reduced costs and improved comfort.
Visible-Infrared Person Re-Identification Using Privileged Intermediate Information
% This paper introduces a novel approach for a creating intermediate virtual domain that acts as bridges between the two main domains (i. e., RGB and IR modalities) during training.
Audio-Visual Fusion for Emotion Recognition in the Valence-Arousal Space Using Joint Cross-Attention
In this paper, we focus on dimensional ER based on the fusion of facial and vocal modalities extracted from videos, where complementary audio-visual (A-V) relationships are explored to predict an individual's emotional states in valence-arousal space.
Constrained Sampling for Class-Agnostic Weakly Supervised Object Localization
Then, foreground and background pixels are sampled from these regions in order to train a WSOL model for generating activation maps that can accurately localize objects belonging to a specific class.
Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization
In this paper, we propose a method to train deep weakly-supervised object localization (WSOL) models based only on image-class labels to locate object with high confidence.
Hybrid Gromov-Wasserstein Embedding for Capsule Learning
Capsule networks (CapsNets) aim to parse images into a hierarchy of objects, parts, and their relations using a two-step process involving part-whole transformation and hierarchical component routing.
TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos
Our proposed TCAM method achieves a new state-of-art in WSVOL accuracy, and visual results suggest that it can be adapted for subsequent tasks like visual object tracking and detection.
Salient Skin Lesion Segmentation via Dilated Scale-Wise Feature Fusion Network
Skin lesion detection in dermoscopic images is essential in the accurate and early diagnosis of skin cancer by a computerized apparatus.
Enhanced Single-shot Detector for Small Object Detection in Remote Sensing Images
In IPSSD, single-shot detector is adopted combined with an image pyramid network to extract semantically strong features for generating candidate regions.
Leveraging Uncertainty for Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images
Our method is composed of two networks: a localizer that yields segmentation mask, followed by a classifier.
Knowledge Distillation for Multi-Target Domain Adaptation in Real-Time Person Re-Identification
Despite the recent success of deep learning architectures, person re-identification (ReID) remains a challenging problem in real-word applications.
Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth Boxes
Semi- and weakly-supervised learning have recently attracted considerable attention in the object detection literature since they can alleviate the cost of annotation needed to successfully train deep learning models.
A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition
Specifically, we propose a joint cross-attention model that relies on the complementary relationships to extract the salient features across A-V modalities, allowing for accurate prediction of continuous values of valence and arousal.
Facial Expression Analysis Using Decomposed Multiscale Spatiotemporal Networks
Our extensive experiments on challenging datasets show that the DMSN-C block is effective for depression detection, whereas the DMSN-A block is efficient for pain estimation.
Dynamic Template Selection Through Change Detection for Adaptive Siamese Tracking
Results indicate that integrating our proposed method into state-of-art adaptive Siamese trackers can increase the potential benefits of a template update strategy, and significantly improve performance.
Generative Target Update for Adaptive Siamese Tracking
This paper proposes a model adaptation method for Siamese trackers that uses a generative model to produce a synthetic template from the object search regions of several previous frames, rather than directly using the tracker output.
Negative Evidence Matters in Interpretable Histology Image Classification
The CNN is exploited to collect both positive and negative evidence at the pixel level to train the decoder.
Cross Attentional Audio-Visual Fusion for Dimensional Emotion Recognition
Results indicate that our cross-attentional A-V fusion model is a cost-effective approach that outperforms state-of-the-art fusion approaches.
F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling
Interpolation is required to restore full size CAMs, yet it does not consider the statistical properties of objects, such as color and texture, leading to activations with inconsistent boundaries, and inaccurate localizations.
Transductive Few-Shot Learning: Clustering is All You Need?
Surprisingly, we found that even standard clustering procedures (e. g., K-means), which correspond to particular, non-regularized cases of our general model, already achieve competitive performances in comparison to the state-of-the-art in few-shot learning.
Holistic Guidance for Occluded Person Re-Identification
Hence, our proposed student-teacher framework is trained to address the occlusion problem by matching the distributions of between- and within-class distances (DCDs) of occluded samples with that of holistic (non-occluded) samples, thereby using the latter as a soft labeled reference to learn well separated DCDs.
Incremental Multi-Target Domain Adaptation for Object Detection with Efficient Domain Transfer
Recent advances in unsupervised domain adaptation have significantly improved the recognition accuracy of CNNs by alleviating the domain shift between (labeled) source and (unlabeled) target data distributions.
Weakly Supervised Learning for Facial Behavior Analysis : A Review
In this paper, we provide a comprehensive review of weakly supervised learning (WSL) approaches for facial behavior analysis with both categorical as well as dimensional labels along with the challenges and potential research directions associated with it.
Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains
Our proposed approach is compared against state-of-the-art methods for compression and STDA of CNNs on the Office31 and ImageClef-DA image classification datasets.
Image Synthesis with Adversarial Networks: a Comprehensive Survey and Case Studies
However, there is a lack of comprehensive review in this field, especially lack of a collection of GANs loss-variant, evaluation metrics, remedies for diverse image generation, and stable training.
Augmented Lagrangian Adversarial Attacks
Our attack enjoys the generality of penalty methods and the computational efficiency of distance-customized algorithms, and can be readily used for a wide set of distances.
Continuous Emotion Recognition with Spatiotemporal Convolutional Neural Networks
In this paper, we investigate the suitability of state-of-the-art deep learning architectures based on convolutional neural networks (CNNs) for continuous emotion recognition using long video sequences captured in-the-wild.
Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertainty
We propose novel regularization terms, which enable the model to seek both non-discriminative and discriminative regions, while discouraging unbalanced segmentations.
Temporal Stochastic Softmax for 3D CNNs: An Application in Facial Expression Recognition
The proposed softmax strategy provides several advantages: a reduced computational complexity due to efficient clip sampling, and an improved accuracy since temporal weighting focuses on more relevant clips during both training and inference.
Facial Expression Recognition
Facial Expression Recognition (FER)
Deep DA for Ordinal Regression of Pain Intensity Estimation Using Weakly-Labeled Videos
The WSDA-OR model enforces ordinal relationships among the intensity levels as-signed to the target sequences, and associates multiple relevant frames to sequence-level labels (instead of a single frame).
Deep Active Learning for Joint Classification & Segmentation with Weak Annotator
CNN visualization and interpretation methods, like class-activation maps (CAMs), are typically used to highlight the image regions linked to class predictions.
Deep Domain Adaptation for Ordinal Regression of Pain Intensity Estimation Using Weakly-Labelled Videos
Estimation of pain intensity from facial expressions captured in videos has an immense potential for health care applications.
A Flow-Guided Mutual Attention Network for Video-Based Person Re-Identification
Our Mutual Attention network relies on the joint spatial attention between image and optical flow features maps to activate a common set of salient features across them.
Optical Flow Estimation
Video-Based Person Re-Identification
Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification
We argue that for pair-wise matchers that rely on metric learning, e. g., Siamese networks for person ReID, the unsupervised domain adaptation (UDA) objective should consist in aligning pair-wise dissimilarity between domains, rather than aligning feature representations.
Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillation
Unsupervised domain adaptation (UDA) seeks to alleviate the problem of domain shift between the distribution of unlabeled data from the target domain w. r. t.
Ranked #3 on
Multi-target Domain Adaptation
on Office-31
Laplacian Regularized Few-Shot Learning
Our transductive inference does not re-train the base model, and can be viewed as a graph clustering of the query set, subject to supervision constraints from the support set.
Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation
In both datasets, results indicate that our method can achieve the highest level of accuracy while requiring a comparable or lower time complexity.
Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision
Particularly, we leverage a classical tightness prior to a deep learning setting via imposing a set of constraints on the network outputs.
A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses
Second, we show that, more generally, minimizing the cross-entropy is actually equivalent to maximizing the mutual information, to which we connect several well-known pairwise losses.
Ranked #12 on
Metric Learning
on CARS196
(using extra training data)
Dual-Triplet Metric Learning for Unsupervised Domain Adaptation in Video-Based Face Recognition
To this end, a dual-triplet loss is introduced for metric learning, where two triplets are constructed using video data from a source camera, and a new target camera.
Convolutional STN for Weakly Supervised Object Localization
Weakly supervised object localization is a challenging task in which the object of interest should be localized while learning its appearance.
Non-parametric Uni-modality Constraints for Deep Ordinal Classification
We propose a new constrained-optimization formulation for deep ordinal classification, in which uni-modality of the label distribution is enforced implicitly via a set of inequality constraints over all the pairs of adjacent labels.
Ranked #1 on
Historical Color Image Dating
on HCI
(MAE metric)
Cross-Domain Face Synthesis using a Controllable GAN
This allows generating realistic synthetic face images that reflects capture conditions in the target domain while controlling the GAN output to generate faces under desired pose conditions.
On the Interaction Between Deep Detectors and Siamese Trackers in Video Surveillance
However, bounding boxes provided by a state-of-the-art detector are noisy, due to changes in appearance, background and occlusion, which can cause the tracker to drift.
Deep Weakly-Supervised Domain Adaptation for Pain Localization in Videos
Automatic pain assessment has an important potential diagnostic value for populations that are incapable of articulating their pain experiences.
A Paired Sparse Representation Model for Robust Face Recognition from a Single Sample
In order to account for non-linear variations due to pose, a paired sparse representation model is introduced allowing for joint use of variational information and synthetic face images.
Emotion Recognition with Spatial Attention and Temporal Softmax Pooling
Video-based emotion recognition is a challenging task because it requires to distinguish the small deformations of the human face that represent emotions, while being invariant to stronger visual differences due to different identities.
Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
Four key challenges are identified for the application of deep WSOL methods in histology -- under/over activation of CAMs, sensitivity to thresholding, and model selection.
Min-max Entropy for Weakly Supervised Pointwise Localization
Pointwise localization allows more precise localization and accurate interpretability, compared to bounding box, in applications where objects are highly unstructured such as in medical domain.
Multimodal Fusion with Deep Neural Networks for Audio-Video Emotion Recognition
This paper presents a novel deep neural network (DNN) for multimodal fusion of audio, video and text modalities for emotion recognition.
Exploiting Prunability for Person Re-Identification
Then, these techniques are analysed according to their pruningcriteria and strategy, and according to different scenarios for exploiting pruningmethods to fine-tuning networks to target domains.
Audio-Visual Kinship Verification
Then, early and late fusion methods are evaluated on the TALKIN dataset for the study of kinship verification with both face and voice modalities.
Progressive Gradient Pruning for Classification, Detection and DomainAdaptation
Although deep neural networks (NNs) have achievedstate-of-the-art accuracy in many visual recognition tasks, the growing computational complexity and energy con-sumption of networks remains an issue, especially for ap-plications on platforms with limited resources and requir-ing real-time processing.
Variational Fair Clustering
We derive a general tight upper bound based on a concave-convex decomposition of our fairness term, its Lipschitz-gradient property and the Pinsker's inequality.
Curriculum semi-supervised segmentation
This study investigates a curriculum-style strategy for semi-supervised CNN segmentation, which devises a regression network to learn image-level information such as the size of a target region.
Constrained Deep Networks: Lagrangian Optimization via Log-Barrier Extensions
While sub-optimality is not guaranteed for non-convex problems, this result shows that log-barrier extensions are a principled way to approximate Lagrangian optimization for constrained CNNs via implicit dual variables.
Boundary loss for highly unbalanced segmentation
We propose a boundary loss, which takes the form of a distance metric on the space of contours, not regions.
Brain Lesion Segmentation From Mri
Ischemic Stroke Lesion Segmentation
+4
Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses
Research on adversarial examples in computer vision tasks has shown that small, often imperceptible changes to an image can induce misclassification, which has security implications for a wide range of image processing systems.
Scalable Laplacian K-modes
Furthermore, we show that the density modes can be obtained as byproducts of the assignment variables via simple maximum-value operations whose additional computational cost is linear in the number of data points.
Cross-Modal Distillation for RGB-Depth Person Re-Identification
Person re-identification is a key challenge for surveillance across multiple sensors.
A Comparison of CNN-based Face and Head Detectors for Real-Time Video Surveillance Applications
Detecting faces and heads appearing in video feeds are challenging tasks in real-world video surveillance applications due to variations in appearance, occlusions and complex backgrounds.
Multi-region segmentation of bladder cancer structures in MRI with progressive dilated convolutional networks
Precise segmentation of bladder walls and tumor regions is an essential step towards non-invasive identification of tumor stage and grade, which is critical for treatment decision and prognosis of patients with bladder cancer (BC).
Constrained-CNN losses for weakly supervised segmentation
To the best of our knowledge, the method of [Pathak et al., 2015] is the only prior work that addresses deep CNNs with linear constraints in weakly supervised segmentation.
Deep Learning Architectures for Face Recognition in Video Surveillance
In video-based FR systems, facial models of target individuals are designed a priori during enrollment using a limited number of reference still images or video data.
Domain-Specific Face Synthesis for Video Face Recognition from a Single Sample Per Person
A compact set of synthetic faces is generated that resemble individuals of interest under the capture conditions relevant to the OD.
Modeling Information Flow Through Deep Neural Networks
This paper proposes a principled information theoretic analysis of classification for deep neural network structures, e. g. convolutional neural networks (CNN).
Bag-Level Aggregation for Multiple Instance Active Learning in Instance Classification Problems
In such cases, active learning (AL) can reduce labeling costs for training a classifier by querying the expert to provide the labels of most informative instances.
Robust Face Tracking using Multiple Appearance Models and Graph Relational Learning
This paper addresses the problem of appearance matching across different challenges while doing visual face tracking in real-world scenarios.
Progressive Boosting for Class Imbalance
Results show that PBoost can outperform state of the art techniques in terms of both accuracy and complexity over different levels of imbalance and overlap between classes.
Tracking using Numerous Anchor points
In this paper, an online adaptive model-free tracker is proposed to track single objects in video sequences to deal with real-world tracking challenges like low-resolution, object deformation, occlusion and motion blur.
Multiple Instance Learning: A Survey of Problem Characteristics and Applications
Multiple instance learning (MIL) is a form of weakly supervised learning where training instances are arranged in sets, called bags, and a label is provided for the entire bag.
Feature Learning from Spectrograms for Assessment of Personality Traits
The number of features, and difficulties linked to the feature extraction process are greatly reduced as only one type of descriptors is used, for which the 6 parameters can be tuned automatically.
Offline Signature-Based Fuzzy Vault (OSFV: Review and New Results
An offline signature-based fuzzy vault (OSFV) is a bio-cryptographic implementation that uses handwritten signature images as biometrics instead of traditional passwords to secure private cryptographic keys.
Automatic Image Registration in Infrared-Visible Videos using Polygon Vertices
To achieve a global affine transformation that maximises the overlapping of infrared and visible foreground pixels, the matched keypoints of each local shape polygon are stored temporally in a buffer for a few number of frames.
