Matryoshka: Exploiting the Over-Parametrization of Deep Learning Models for Covert Data Transmission
Human-Centric Transformer for Domain Adaptive Action Recognition
On the Distillation of Stories for Transferring Narrative Arcs in Collections of Independent Media
VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Model
Robust Multimodal Learning With Missing Modalities via Parameter-Efficient Adaptation
FocalPose++: Focal Length and Object Pose Estimation via Render and Compare
Sparse Non-Local CRF With Applications
Intelligent Bionic Polarization Orientation Method Using Biological Neuron Model for Harsh Conditions
Continuous-Time Object Segmentation Using High Temporal Resolution Event Camera
Competing for Pixels: A Self-Play Algorithm for Weakly-Supervised Semantic Segmentation
Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion
Pixel is All You Need: Adversarial Spatio-Temporal Ensemble Active Learning for Salient Object Detection
Towards Data-And Knowledge-Driven AI: A Survey on Neuro-Symbolic Computing
GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection
Enabling Energy-Efficient Deployment of Large Language Models on Memristor Crossbar: A Synergy of Large and Small
VATr++: Choose Your Words Wisely for Handwritten Text Generation
OffsetNet: Towards Efficient Multiple Object Tracking, Detection, and Segmentation
Diffusion Models for Imperceptible and Transferable Adversarial Attack
PSRR-MaxpoolNMS++: Fast Non-Maximum Suppression With Discretization and Pooling
ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model With Implicit Neural Representations
Evolved Hierarchical Masking for Self-Supervised Learning
Universal Fingerprint Generation: Controllable Diffusion Model With Multimodal Conditions
Prompt Tuning of Deep Neural Networks for Speaker-Adaptive Visual Speech Recognition
Anti-Forgetting Adaptation for Unsupervised Person Re-Identification
Noise Self-Regression: A New Learning Paradigm to Enhance Low-Light Images Without Task-Related Data
Language-Inspired Relation Transfer for Few-Shot Class-Incremental Learning
Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data
Illuminating Salient Contributions in Neuron Activation With Attribution Equilibrium
Disentangling Before Composing: Learning Invariant Disentangled Features for Compositional Zero-Shot Learning
FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations
Recent Advances in Optimal Transport for Machine Learning
Efficient Analysis of Overdispersed Data Using an Accurate Computation of the Dirichlet Multinomial Distribution
360SFUDA++: Towards Source-Free UDA for Panoramic Segmentation by Learning Reliable Category Prototypes
Multi-Modality Multi-Attribute Contrastive Pre-Training for Image Aesthetics Computing
Adaptive Learning for Dynamic Features and Noisy Labels
Minimum Latency Deep Online Video Stabilization and Its Extensions
The Decoupling Concept Bottleneck Model
Event-Enhanced Snapshot Compressive Videography at 10K FPS
FSD V2: Improving Fully Sparse 3D Object Detection With Virtual Voxels
Estimating Information Theoretic Measures via Multidimensional Gaussianization
Fast and Functional Structured Data Generators Rooted in Out-of-Equilibrium Physics
Online Learning Under a Separable Stochastic Approximation Framework
Unsupervised Degradation Representation Learning for Unpaired Restoration of Images and Point Clouds
Adaptive Neural Message Passing for Inductive Learning on Hypergraphs
EventHDR: From Event to High-Speed HDR Videos and Beyond
PSVMA+: Exploring Multi-Granularity Semantic-Visual Adaption for Generalized Zero-Shot Learning
Stabilizing and Accelerating Federated Learning on Heterogeneous Data With Partial Client Participation
Weakly Supervised Monocular 3D Object Detection by Spatial-Temporal View Consistency
Prototype-Guided Attention Distillation for Discriminative Person Search