Search Results for author:
Found 8 papers, 5 papers with code
DreamPolisher: Towards High-Quality Text-to-3D Generation via Geometric Diffusion
We present DreamPolisher, a novel Gaussian Splatting based method with geometric guidance, tailored to learn cross-view consistency and intricate detail from textual descriptions.
Text-Driven Image Editing via Learnable Regions
Language has emerged as a natural interface for image editing.
SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training
Coupling all these designs allows our method to enjoy both competitive performances on text-to-video retrieval and video question answering tasks, and much less pre-training costs by 1. 9X or more.
REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering
Specifically, we observe that in most state-of-the-art knowledge-based VQA methods: 1) visual features are extracted either from the whole image or in a sliding window manner for retrieving knowledge, and the important relationship within/among object regions is neglected; 2) visual features are not well utilized in the final answering model, which is counter-intuitive to some extent.
Ranked #11 on
Visual Question Answering (VQA)
on OK-VQA
Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding
Our method leverages an off-the-shelf object detector to identify visual objects from unlabeled images, and then language queries for these objects are obtained in an unsupervised fashion with a pseudo-query generation module.
AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition
Recent works have shown that the computational efficiency of video recognition can be significantly improved by reducing the spatial redundancy.
Cross-Stage Transformer for Video Learning
By inserting the proposed cross-stage mechanism in existing spatial and temporal transformer blocks, we build a separable transformer network for video learning based on ViT structure, in which self-attentions and features are progressively aggregated from one block to the next.
Self-Supervised Video Representation Learning with Meta-Contrastive Network
Our method contains two training stages based on model-agnostic meta learning (MAML), each of which consists of a contrastive branch and a meta branch.
Ranked #28 on
Self-Supervised Action Recognition
on HMDB51
