Search Results for author:
Found 30 papers, 8 papers with code
Mimir: Improving Video Diffusion Models for Precise Text Understanding
Text serves as the key control signal in video generation due to its narrative nature.
In-Context LoRA for Diffusion Transformers
While task-specific in terms of tuning data, our framework remains task-agnostic in architecture and pipeline, offering a powerful tool for the community and providing valuable insights for further research on product-level task-agnostic generation systems.
Group Diffusion Transformers are Unsupervised Multitask Learners
In this work, we introduce Group Diffusion Transformers (GDTs), a novel framework that unifies diverse visual generation tasks by redefining them as a group generation problem.
DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control
In this paper, we present DreamVideo-2, a zero-shot video customization framework capable of generating videos with a specific subject and motion trajectory, guided by a single image and a bounding box sequence, respectively, and without the need for test-time fine-tuning.
Zero-shot Image Editing with Reference Imitation
Image editing serves as a practical yet challenging task considering the diverse demands from users, where one of the hardest parts is to precisely describe how the edited image should look like.
FlashFace: Human Image Personalization with High-fidelity Identity Preservation
This work presents FlashFace, a practical tool with which users can easily personalize their own photos on the fly by providing one or a few reference face images and a text prompt.
Spatio-Temporal Field Neural Networks for Air Quality Inference
The air quality inference problem aims to utilize historical data from a limited number of observation sites to infer the air quality index at an unknown location.
Check Locate Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation
To align the generated image with layout instructions we present a training-free layout calibration system SimM that intervenes in the generative process on the fly during inference time.
LivePhoto: Real Image Animation with Text-guided Motion Control
In particular, considering the facts that (1) text can only describe motions roughly (e. g., regardless of the moving speed) and (2) text may include both content and motion descriptions, we introduce a motion intensity estimation module as well as a text re-weighting module to reduce the ambiguity of text-to-motion mapping.
Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation
To align the generated image with layout instructions, we present a training-free layout calibration system SimM that intervenes in the generative process on the fly during inference time.
Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation
Experimental results show that existing subject-driven customization methods fail to learn the representative characteristics of actions and struggle in decoupling actions from context features, including appearance.
Incentive Mechanism Design for Unbiased Federated Learning with Randomized Client Participation
Incentive mechanism is crucial for federated learning (FL) when rational clients do not have the same interests in the global model as the server.
Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning
Recent compositional zero-shot learning (CZSL) methods adapt pre-trained vision-language models (VLMs) by constructing trainable prompts only for composed state-object pairs.
ViM: Vision Middleware for Unified Downstream Transferring
ViM consists of a zoo of lightweight plug-in modules, each of which is independently learned on a midstream dataset with a shared frozen backbone.
UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training
This work presents a unified knowledge protocol, called UKnow, which facilitates knowledge-based studies from the perspective of data.
Grow and Merge: A Unified Framework for Continuous Categories Discovery
Although a number of studies are devoted to novel category discovery, most of them assume a static setting where both labeled and unlabeled data are given at once for finding new categories.
SsciBERT: A Pre-trained Language Model for Social Science Texts
The academic literature of social sciences records human civilization and studies human social problems.
Rethinking Supervised Pre-training for Better Downstream Transferring
Though for most cases, the pre-training stage is conducted based on supervised methods, recent works on self-supervised pre-training have shown powerful transferability and even outperform supervised pre-training on multiple downstream tasks.
Exploring Stronger Feature for Temporal Action Localization
Temporal action localization aims to localize starting and ending time with action category.
Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling
Then our proposed Local-Global Background Modeling Network (LGBM-Net) is trained to localize instances by using only video-level labels based on Multi-Instance Learning (MIL).
Weakly-supervised Learning
Weakly-supervised Temporal Action Localization
+1
Proposal Relation Network for Temporal Action Detection
We calculate the detection results by assigning the proposals with corresponding classification results.
Ranked #3 on
Temporal Action Localization
on ActivityNet-1.3
(using extra training data)
Relation Modeling in Spatio-Temporal Action Localization
This paper presents our solution to the AVA-Kinetics Crossover Challenge of ActivityNet workshop at CVPR 2021.
Ranked #4 on
Spatio-Temporal Action Localization
on AVA-Kinetics
(using extra training data)
A Stronger Baseline for Ego-Centric Action Detection
This technical report analyzes an egocentric video action detection method we used in the 2021 EPIC-KITCHENS-100 competition hosted in CVPR2021 Workshop.
Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition
In this paper, we present empirical results for training a stronger video vision transformer on the EPIC-KITCHENS-100 Action Recognition dataset.
View-Guided Point Cloud Completion
This paper presents a view-guided solution for the task of point cloud completion.
Ranked #3 on
Point Cloud Completion
on ShapeNet-ViPC
Incremental Learning on Growing Graphs
To tackle this problem, we introduce incremental graph learning (IGL), a general framework to formulate the learning on growing graphs in an incremental manner, where traditional graph learning method could be deployed as a basic model.
Event Stream Super-Resolution via Spatiotemporal Constraint Learning
Therefore, it is imperative to explore the algorithm of event stream super-resolution, which is a non-trivial task due to the sparsity and strong spatio-temporal correlation of the events from an event camera.
Design of High-Frequency Trading Algorithm Based on Machine Learning
Based on iterative optimization and activation function in deep learning, we proposed a new analytical framework of high-frequency trading information, that reduced structural loss in the assembly of Volume-synchronized probability of Informed Trading ($VPIN$), Generalized Autoregressive Conditional Heteroscedasticity (GARCH) and Support Vector Machine (SVM) to make full use of the order book information.
Trading and Market Microstructure
MeshNet: Mesh Neural Network for 3D Shape Representation
However, there is little effort on using mesh data in recent years, due to the complexity and irregularity of mesh data.
