From speaker to dubber: movie dubbing with prosody and duration consistency learning
Movie Dubbing aims to convert scripts into speeches that align with the given movie clip in
both temporal and emotional aspects while preserving the vocal timbre of one brief …
both temporal and emotional aspects while preserving the vocal timbre of one brief …
Training-free video temporal grounding using large-scale pre-trained models
Video temporal grounding aims to identify video segments within untrimmed videos that are
most relevant to a given natural language query. Existing video temporal localization models …
most relevant to a given natural language query. Existing video temporal localization models …
It Takes Two: Accurate Gait Recognition in the Wild via Cross-granularity Alignment
Existing studies for gait recognition primarily utilized sequences of either binary silhouette or
human parsing to encode the shapes and dynamics of persons during walking. Silhouettes …
human parsing to encode the shapes and dynamics of persons during walking. Silhouettes …
Stochastic Context Consistency Reasoning for Domain Adaptive Object Detection
Domain Adaptive Object Detection (DAOD) aims to improve the adaptation of the detector for
the unlabeled target domain by the labeled source domain. Recent advances leverage a …
the unlabeled target domain by the labeled source domain. Recent advances leverage a …
EventHDR: From Event to High-Speed HDR Videos and Beyond
Event cameras are innovative neuromorphic sensors that asynchronously capture the scene
dynamics. Due to the event-triggering mechanism, such cameras record event streams with …
dynamics. Due to the event-triggering mechanism, such cameras record event streams with …
Mitigate Catastrophic Remembering via Continual Knowledge Purification for Noisy Lifelong Person Re-Identification
Current Lifelong Person Re-Identification (LReID) methods focus on tackling a clean data
stream with accurate labels. When noisy data with incorrect labels are given, their …
stream with accurate labels. When noisy data with incorrect labels are given, their …
Progressive Prototype Evolving for Dual-Forgetting Mitigation in Non-Exemplar Online Continual Learning
Online Continual Learning (OCL) aims at learning a model through a sequence of single-
pass data, usually encountering the challenges of catastrophic forgetting both between …
pass data, usually encountering the challenges of catastrophic forgetting both between …
InsVP: Efficient Instance Visual Prompting from Image Itself
Visual prompting is an efficient methodology for finetuning pretrained visual models by
introducing a small number of learnable parameters while keeping the backbone frozen …
introducing a small number of learnable parameters while keeping the backbone frozen …
Object-Aware NIR-to-Visible Translation
Y Gao, L Gu, Q Liu, Y Fu - European Conference on Computer Vision, 2024 - Springer
While near-infrared (NIR) imaging is essential for assisted driving and safety monitoring
systems, its monochromatic nature hinders its broader application, which prompts the …
systems, its monochromatic nature hinders its broader application, which prompts the …
Privacy-enhanced prototype-based federated cross-modal hashing for cross-modal retrieval
Cross-modal hashing is widely used for efficient similarity searches, improving data
processing efficiency, and reducing storage costs. Existing cross-modal hashing methods …
processing efficiency, and reducing storage costs. Existing cross-modal hashing methods …