Elisa Ricci

62

Papers

155

Total Citations

Papers (62)

Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction

NeurIPS 2017arXiv

SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection

Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models

Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers

Compositional Caching for Training-free Open-vocabulary Attribute Detection

FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models

ConViS-Bench: Estimating Video Similarity Through Semantic Concepts

Can Text-to-Video Generation help Video-Language Alignment?

Test-Time Zero-Shot Temporal Action Localization

Self-Adaptive Matrix Completion for Heart Rate Estimation From Face Videos Under Realistic Conditions

Recognizing Emotions From Abstract Paintings Using Non-Linear Matrix Completion

Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation

Learning Cross-Modal Deep Representations for Robust Pedestrian Detection

Viraliency: Pooling Local Virality

Boosting Domain Adaptation by Discovering Latent Domains

Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation

Every Smile Is Unique: Landmark-Guided Diverse Smile Generation

Animating Arbitrary Objects via Deep Motion Transfer

AdaGraph: Unifying Predictive and Continuous Domain Adaptation Through Graphs

Unsupervised Domain Adaptation Using Feature-Whitening and Consensus Loss

Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation

Online Depth Learning Against Forgetting in Monocular Videos

Modeling the Background for Incremental Learning in Semantic Segmentation

Neighborhood Contrastive Learning for Novel Class Discovery

Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation

Playable Video Generation

Self-Supervised Models Are Continual Learners

Playable Environments: Video Manipulation in Space and Time

AutoLabel: CLIP-Based Framework for Open-Set Video Domain Adaptation

Semi-Supervised Learning Made Simple With Self-Supervised Clustering

Novel Class Discovery for 3D Point Cloud Semantic Segmentation

Quantum Multi-Model Fitting

Uncovering Interactions and Interactors: Joint Estimation of Head, Body Orientation and F-Formations From Surveillance Videos

AutoDIAL: Automatic DomaIn Alignment Layers

Budget-Aware Adapters for Multi-Domain Learning

Viewing Graph Solvability via Cycle Consistency

A Unified Objective for Novel Class Discovery

Are We Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection?

Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction

Click To Move: Controlling Video Generation With Sparse Motion

A Soft Nearest-Neighbor Framework for Continual Semi-Supervised Learning

Object-aware Gaze Target Detection

Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation

Towards Generalization Across Depth for Monocular 3D Object Detection

Towards Recognizing Unseen Categories in Unseen Domains

Online Continual Learning under Extreme Memory Constraints

Learning to Cluster under Domain Shift

Uncertainty-Guided Source-Free Domain Adaptation

Quantum Motion Segmentation

Class-Incremental Novel Class Discovery

GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation

CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation

The Unreasonable Effectiveness of Large Language-Vision Models for Source-Free Video Domain Adaptation

Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages

Training-Free Personalization via Retrieval and Reasoning on Fingerprints

On Large Multimodal Models as Open-World Image Classifiers

Superpowering Open-Vocabulary Object Detectors for X-ray Vision

Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis

MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning

Harnessing Large Language Models for Training-free Video Anomaly Detection

First Order Motion Model for Image Animation

Vocabulary-free Image Classification