Search Results for author:
Found 11 papers, 5 papers with code
Cyc3D: Fine-grained Controllable 3D Generation via Cycle Consistency Regularization
Given an initial viewpoint and a control signal, a novel view is rendered from the generated 3D content, from which the extracted condition is used to regenerate the 3D content.
CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion
CFSum exploits video, text, and audio modal features as input, and incorporates a two-stage transformer-based feature fusion framework to fully utilize modality-unique information.
Visual Object Tracking across Diverse Data Modalities: A Review
Specifically, we first review three types of mainstream single-modal VOT, including RGB, thermal infrared and point cloud tracking.
TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-On
However, the clothing identity uncontrollability and training inefficiency of existing diffusion-based methods, which struggle to maintain the identity even with full parameter training, are significant limitations that hinder the widespread applications.
SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking
Multimodal Visual Object Tracking (VOT) has recently gained significant attention due to its robustness.
Ranked #29 on
Rgb-T Tracking
on RGBT234
FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio
In this paper, we abstract the process of people hearing speech, extracting meaningful cues, and creating various dynamically audio-consistent talking faces, termed Listening and Imagining, into the task of high-fidelity diverse talking faces generation from a single audio.
M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition
In this paper, we introduce a novel Multimodal, Multi-task CLIP adapting framework named \name to address these challenges, preserving both high supervised performance and robust transferability.
Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching
Class prototype construction and matching are core aspects of few-shot action recognition.
MA-FSAR: Multimodal Adaptation of CLIP for Few-Shot Action Recognition
To tackle these issues, we introduce MA-FSAR, a framework that employs the Parameter-Efficient Fine-Tuning (PEFT) technique to enhance the CLIP visual encoder in terms of action-related temporal and semantic representations.
Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition
In this paper, we propose SloshNet, a new framework that revisits the spatial and temporal modeling for few-shot action recognition in a finer manner.
ActionCLIP: A New Paradigm for Video Action Recognition
Moreover, to handle the deficiency of label texts and make use of tremendous web data, we propose a new paradigm based on this multimodal learning framework for action recognition, which we dub "pre-train, prompt and fine-tune".
Ranked #2 on
Action Recognition In Videos
on Kinetics-400
