Search Results for author:
Found 78 papers, 31 papers with code
Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery
Despite its broad application and interest, it remains a challenging problem in part due to the vast range of conditions under which it must be robust.
Interactive Garment Recommendation with User in the Loop
Recommending fashion items often leverages rich user profiles and makes targeted suggestions based on past history and previous purchases.
Neuromorphic Face Analysis: a Survey
Neuromorphic sensors, also known as event cameras, are a class of imaging devices mimicking the function of biological visual systems.
Neuromorphic Valence and Arousal Estimation
Recognizing faces and their underlying emotions is an important aspect of biometrics.
Restoration of Analog Videos Using Swin-UNet
In this paper, we present a system to restore analog videos of historical archives.
Ranked #2 on
Analog Video Restoration
on TAPE
Perceptual Quality Improvement in Videoconferencing using Keyframes-based GAN
Given that, in this context, the speaker is typically in front of the camera and remains the same for the entire duration of the transmission, we can maintain a set of reference keyframes of the person from the higher-quality I-frames that are transmitted within the video stream and exploit them to guide the visual quality improvement; a novel aspect of this approach is the update policy that maintains and updates a compact and effective set of reference keyframes.
FLODCAST: Flow and Depth Forecasting via Multimodal Recurrent Architectures
We train the proposed model to also perform predictions for several timesteps in the future.
Deepfake detection by exploiting surface anomalies: the SurFake approach
In particular, when an image (video) is captured the overall geometry of the scene (e. g. surfaces) and the acquisition process (e. g. illumination) determine a univocal environment that is directly represented by the image pixel values; all these intrinsic relations are possibly changed by the deepfake generation process.
Addressing Limitations of State-Aware Imitation Learning for Autonomous Driving
We feed the state of the vehicle along with the representation of the environment as a special token of the transformer and propagate it throughout the network.
Reference-based Restoration of Digitized Analog Videotapes
We design a transformer-based Swin-UNet network that exploits both neighboring and reference frames via our Multi-Reference Spatial Feature Fusion (MRSFF) blocks.
Ranked #1 on
Analog Video Restoration
on TAPE
ARNIQA: Learning Distortion Manifold for Image Quality Assessment
In this work, we propose a self-supervised approach named ARNIQA (leArning distoRtion maNifold for Image Quality Assessment) for modeling the image distortion manifold to obtain quality representations in an intrinsic manner.
Ranked #2 on
No-Reference Image Quality Assessment
on CSIQ
Blind Image Quality Assessment
No-Reference Image Quality Assessment
+1
Mapping Memes to Words for Multimodal Hateful Meme Classification
Multimodal image-text memes are prevalent on the internet, serving as a unique form of communication that combines visual and textual elements to convey humor, ideas, or emotions.
Ranked #1 on
Hateful Meme Classification
on HarMeme
Exploiting CLIP-based Multi-modal Approach for Artwork Classification and Retrieval
Given the recent advances in multimodal image pretraining where visual models trained with semantically dense textual supervision tend to have better generalization capabilities than those trained using categorical attributes or through unsupervised techniques, in this work we investigate how recent CLIP model can be applied in several tasks in artwork domain.
DiffDefense: Defending against Adversarial Attacks via Diffusion Models
This paper presents a novel reconstruction method that leverages Diffusion Models to protect machine learning classifiers against adversarial attacks, all without requiring any modifications to the classifiers themselves.
3D Pose Nowcasting: Forecast the Future to Improve the Present
Technologies to enable safe and effective collaboration and coexistence between humans and robots have gained significant importance in the last few years.
Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features
Given a query composed of a reference image and a relative caption, the Composed Image Retrieval goal is to retrieve images visually similar to the reference one that integrates the modifications expressed by the caption.
Ranked #6 on
Image Retrieval
on CIRR
Diffusion Based Augmentation for Captioning and Retrieval in Cultural Heritage
Cultural heritage applications and advanced machine learning models are creating a fruitful synergy to provide effective and accessible ways of interacting with artworks.
ECO: Ensembling Context Optimization for Vision-Language Models
Among these, the CLIP model has shown remarkable capabilities for zero-shot transfer by matching an image and a custom textual prompt in its latent space.
4DSR-GCN: 4D Video Point Cloud Upsampling using Graph Convolutional Networks
Time varying sequences of 3D point clouds, or 4D point clouds, are now being acquired at an increasing pace in several applications (e. g., LiDAR in autonomous or assisted driving).
Transformer-based Graph Neural Networks for Outfit Generation
We attempt to bridge the gap between outfit recommendation and generation by leveraging a graph-based representation of items in a collection.
Neuromorphic Event-based Facial Expression Recognition
Recently, event cameras have shown large applicability in several computer vision fields especially concerning tasks that require high temporal resolution.
Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images
Recent advancements in diffusion models have enabled the generation of realistic deepfakes by writing textual prompts in natural language.
Zero-Shot Composed Image Retrieval with Textual Inversion
Composed Image Retrieval (CIR) aims to retrieve a target image based on a query composed of a reference image and a relative caption that describes the difference between the two images.
Maximally Compact and Separated Features with Regular Polytope Networks
Convolutional Neural Networks (CNNs) trained with the Softmax loss are widely used classification models for several vision tasks.
CL2R: Compatible Lifelong Learning Representations
We identify stationarity as the property that the feature representation is required to hold to achieve compatibility and propose a novel training procedure that encourages local and global stationarity on the learned representation.
Forecasting Future Instance Segmentation with Learned Optical Flow and Warping
For an autonomous vehicle it is essential to observe the ongoing dynamics of a scene and consequently predict imminent future scenarios to ensure safety to itself and others.
Learning advisor networks for noisy image classification
In this paper, we introduced the novel concept of advisor network to address the problem of noisy labels in image classification.
Ranked #6 on
Image Classification
on Clothing1M
(using extra training data)
Automatic Estimation of Self-Reported Pain by Trajectory Analysis in the Manifold of Fixed Rank Positive Semi-Definite Matrices
We compared our method to the state-of-the-art on both datasets using different testing protocols, showing the competitiveness of the proposed approach.
Fashion Recommendation Based on Style and Social Events
Overall, we integrate in a state of the art garment recommendation framework a style classifier and an event classifier in order to condition recommendation on a given query.
Generating Multiple 4D Expression Transitions by Learning Face Landmark Trajectories
We thus propose a new model that generates transitions between different expressions, and synthesizes long and composed 4D expressions.
Is GPT-3 all you need for Visual Question Answering in Cultural Heritage?
The use of Deep Learning and Computer Vision in the Cultural Heritage domain is becoming highly relevant in the last few years with lots of applications about audio smart guides, interactive museums and augmented reality.
What makes you, you? Analyzing Recognition by Swapping Face Parts
Deep learning advanced face recognition to an unprecedented accuracy.
Conditioned and Composed Image Retrieval Combining and Partially Fine-Tuning CLIP-Based Features
The proposed method is based on an initial training stage where a simple combination of visual and textual features is used, to fine-tune the CLIP text encoder.
Ranked #3 on
Image Retrieval
on LaSCo
Composed Image Retrieval (CoIR)
Content-Based Image Retrieval
+2
Online Deep Clustering with Video Track Consistency
Several unsupervised and self-supervised approaches have been developed in recent years to learn visual features from large-scale unlabeled datasets.
Contrastive Supervised Distillation for Continual Representation Learning
In this paper, we propose a novel training procedure for the continual representation learning problem in which a neural network model is sequentially learned to alleviate catastrophic forgetting in visual search tasks.
SMEMO: Social Memory for Trajectory Forecasting
Effective modeling of human interactions is of utmost importance when forecasting behaviors such as future trajectories.
Ranked #5 on
Trajectory Prediction
on Stanford Drone
On Modality Bias Recognition and Reduction
From the results on four datasets regarding the above three tasks, our method yields remarkable performance improvements compared with the baselines, demonstrating its superiority on reducing the modality bias problem.
Effective Conditioned and Composed Image Retrieval Combining CLIP-Based Features
the visual content of the query image.
Ranked #9 on
Image Retrieval
on CIRR
CoReS: Compatible Representations via Stationarity
Compatible features enable the direct comparison of old and new learned features allowing to use them interchangeably over time.
Fine-Grained Adversarial Semi-supervised Learning
Our approach leverages unlabeled data with an adversarial optimization strategy in which the internal features representation is obtained with a second-order pooling model.
Partially fake it till you make it: mixing real and fake thermal images for improved object detection
In this paper we propose a novel data augmentation approach for visual content domains that have scarce training datasets, compositing synthetic 3D objects within real scenes.
Sparse to Dense Dynamic 3D Facial Expression Generation
This allows us to learn how the motion of a sparse set of landmarks influences the deformation of the overall face surface, independently from the identity.
Learning Group Activities from Skeletons without Individual Action Labels
To understand human behavior we must not just recognize individual actions but model possibly complex group activity and interactions.
Ranked #8 on
Group Activity Recognition
on Volleyball
AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss
Experimental results demonstrate that our adapted margin cosine loss can greatly enhance the baseline models with an absolute performance gain of 15\% on average, strongly verifying the potential of tackling the language prior problem in VQA from the angle of the answer feature space learning.
Regular Polytope Networks
Typically, a learnable transformation (i. e. the classifier) is placed at the end of such models returning a value for each class used for classification.
Robust pedestrian detection in thermal imagery using synthesized images
Experimental results demonstrate the effectiveness of our approach: using less than 50\% of available real thermal training data, and relying on synthesized data generated by our model in the domain adaptation phase, our detector achieves state-of-the-art results on the KAIST Multispectral Pedestrian Detection Benchmark; even if more real thermal data is available adding GAN generated images to the training data results in improved performance, thus showing that these images act as an effective form of data augmentation.
Garment Recommendation with Memory Augmented Neural Networks
In particular, we aim at retrieving a variety of modalities in which a certain garment can be combined.
Multiple Future Prediction Leveraging Synthetic Trajectories
Trajectory prediction is an important task, especially in autonomous driving.
Temporal Binary Representation for Event-Based Action Recognition
In this paper we present an event aggregation strategy to convert the output of an event camera into frames processable by traditional Computer Vision algorithms.
Ranked #3 on
Gesture Recognition
on DVS128 Gesture
(using extra training data)
Class-incremental Learning with Pre-allocated Fixed Classifiers
Contrarily to the standard expanding classifier, this allows: (a) the output nodes of future unseen classes to firstly see negative samples since the beginning of learning together with the positive samples that incrementally arrive; (b) to learn features that do not change their geometric configuration as novel classes are incorporated in the learning model.
Inner Eye Canthus Localization for Human Body Temperature Screening
As additional contribution, we enrich the original dataset by using the annotated landmarks to deform and project the 3DMM onto the images.
Modelling the Statistics of Cyclic Activities by Trajectory Analysis on the Manifold of Positive-Semi-Definite Matrices
In this paper, a model is presented to extract statistical summaries to characterize the repetition of a cyclic body action, for instance a gym exercise, for the purpose of checking the compliance of the observed action to a template one and highlighting the parts of the action that are not correctly executed (if any).
Automatic Estimation of Self-Reported Pain by Interpretable Representations of Motion Dynamics
For each video, pain intensity was measured using the dynamics of facial movement using 66 facial points.
A Sparse and Locally Coherent Morphable Face Model for Dense Semantic Correspondence Across Heterogeneous 3D Faces
The 3D Morphable Model (3DMM) is a powerful statistical tool for representing 3D face shapes.
MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction
Autonomous vehicles are expected to drive in complex scenarios with several independent non cooperating agents.
Explaining Autonomous Driving by Learning End-to-End Visual Attention
Current deep learning based autonomous driving approaches yield impressive results also leading to in-production deployment in certain controlled scenarios.
Image Retrieval using Multi-scale CNN Features Pooling
In this paper, we address the problem of image retrieval by learning images representation based on the activations of a Convolutional Neural Network.
Visual Question Answering for Cultural Heritage
This will turn the classic audio guide into a smart personal instructor with which the visitor can interact by asking for explanations focused on specific interests.
Text-to-Image Synthesis Based on Machine Generated Captions
To address this issue, in this paper we propose an approach capable of generating images starting from a given text using conditional GANs trained on uncaptioned images dataset.
Fitting, Comparison, and Alignment of Trajectories on Positive Semi-Definite Matrices with Application to Action Recognition
In this paper, we tackle the problem of action recognition using body skeletons extracted from video sequences.
Fix Your Features: Stationary and Maximally Discriminative Embeddings using Regular Polytope (Fixed Classifier) Networks
Typically, a learnable transformation (i. e. the classifier) is placed at the end of such models returning a value for each class used for classification.
Additional Baseline Metrics for the paper "Extended YouTube Faces: a Dataset for Heterogeneous Open-Set Face Identification"
In this report, we provide additional and corrected results for the paper "Extended YouTube Faces: a Dataset for Heterogeneous Open-Set Face Identification".
Semantic Road Layout Understanding by Generative Adversarial Inpainting
Autonomous driving is becoming a reality, yet vehicles still need to rely on complex sensor fusion to understand the scene they act in.
Memory Based Online Learning of Deep Representations from Video Streams
It is shown that the proposed learning procedure is asymptotically stable and can be effectively used in relevant applications like multiple face identification and tracking from unconstrained video streams.
Unsupervised Incremental Learning of Deep Descriptors From Video Streams
We present a novel unsupervised method for face identity learning from video sequences.
Group Re-Identification via Unsupervised Transfer of Sparse Features Encoding
First, a dictionary of sparse atoms is learned using patches extracted from single person images.
Emotion Recognition by Body Movement Representation on the Manifold of Symmetric Positive Definite Matrices
Emotion recognition is attracting great interest for its potential application in a multitude of real-life situations.
Context-Aware Trajectory Prediction
To this end, we propose a "context-aware" recurrent neural network LSTM model, which can learn and predict human motion in crowded spaces such as a sidewalk, a museum or a shopping mall.
Am I Done? Predicting Action Progress in Videos
In this paper we deal with the problem of predicting action progress in videos.
Deep Generative Adversarial Compression Artifact Removal
Moreover we show that our approach can be used as a pre-processing step for object detection in case images are degraded by compression to a point that state-of-the art detectors fail.
Segmentation Free Object Discovery in Video
In this paper we present a simple yet effective approach to extend without supervision any object proposal from static images to videos.
Automatic Image Annotation via Label Transfer in the Semantic Space
Automatic image annotation is among the fundamental problems in computer vision and pattern recognition, and it is becoming increasingly important in order to develop algorithms that are able to search and browse large-scale image collections.
Compact Hash Codes for Efficient Visual Descriptors Retrieval in Large Scale Databases
In this paper we present an efficient method for visual descriptors retrieval based on compact hash codes computed using a multiple k-means assignment.
A Multi-Camera Image Processing and Visualization System for Train Safety Assessment
In this paper we present a machine vision system to efficiently monitor, analyze and present visual data acquired with a railway overhead gantry equipped with multiple cameras.
Representing 3D Texture on Mesh Manifolds for Retrieval and Recognition Applications
In this paper, we present and experiment a novel approach for representing texture of 3D mesh manifolds using local binary patterns (LBP).
Socializing the Semantic Gap: A Comparative Survey on Image Tag Assignment, Refinement and Retrieval
Where previous reviews on content-based image retrieval emphasize on what can be seen in an image to bridge the semantic gap, this survey considers what people tag about an image.
A Data-Driven Approach for Tag Refinement and Localization in Web Videos
Our approach exploits collective knowledge embedded in user-generated tags and web sources, and visual similarity of keyframes and images uploaded to social sites like YouTube and Flickr, as well as web sources like Google and Bing.
Continuous Localization and Mapping of a Pan Tilt Zoom Camera for Wide Area Tracking
Pan-tilt-zoom (PTZ) cameras are powerful to support object identification and recognition in far-field scenes.
