Search Results for author:
Found 41 papers, 16 papers with code
EEdit : Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing
Inversion-based image editing is rapidly gaining momentum while suffering from significant computation overhead, hindering its application in real-time interactive scenarios.
RadioLLM: Introducing Large Language Model into Cognitive Radio via Hybrid Prompt and Token Reprogrammings
HPTR enables the integration of radio signal features with expert knowledge, while FAF improves the modeling of high-frequency features critical for precise signal processing.
Enhancing Image Generation Fidelity via Progressive Prompts
We find that deeper layers are always responsible for high - level content control, while shallow layers handle low - level content control.
ListConRanker: A Contrastive Text Reranker with Listwise Encoding
Reranker models aim to re-rank the passages based on the semantics similarity between the given query and passages, which have recently received more attention due to the wide application of the Retrieval-Augmented Generation.
H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous Driving
Consequently, it can adaptively integrate all the video contexts of multi-scale temporal resolutions to enhance video understanding.
Follow-Your-MultiPose: Tuning-Free Multi-Character Text-to-Video Generation via Pose Guidance
To tackle this, we propose a novel multi-character video generation framework in a tuning-free manner, which is based on the separated text and pose guidance.
UniPaint: Unified Space-time Video Inpainting via Mixture-of-Experts
In this paper, we present UniPaint, a unified generative space-time video inpainting framework that enables spatial-temporal inpainting and interpolation.
LVP-CLIP:Revisiting CLIP for Continual Learning with Label Vector Pool
Traditional CLIP-based classification methods identify the most similar text label for a test image by comparing their embeddings.
InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences
They struggle to maintain consistency in both the foreground and background during concept swapping, especially when the shape difference is large between objects.
Taming Rectified Flow for Inversion and Editing
To address this issue, we propose RF-Solver, a novel training-free sampler that effectively enhances inversion precision by mitigating the errors in the ODE-solving process of rectified flow.
DiT4Edit: Diffusion Transformer for Image Editing
Compared to UNet, Diffusion Transformers (DiT) demonstrate superior capabilities to effectively capture the long-range dependencies among patches, leading to higher-quality image generation.
Memoryless Multimodal Anomaly Detection via Student-Teacher Network and Signed Distance Learning
In present study, a novel memoryless method MDSS is proposed for multimodal anomaly detection, which employs a light-weighted student-teacher network and a signed distance function to learn from RGB images and 3D point clouds respectively, and complements the anomaly information from the two modalities.
Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation
Coupling with these two designs enables us to generate higher-resolution outpainting videos with rich content while keeping spatial and temporal consistency.
Freehand Sketch Generation from Mechanical Components
To address this issue, we design a two-stage generative framework mimicking the human sketching behavior pattern, called MSFormer, which is the first time to produce humanoid freehand sketches tailored for mechanical components.
Alleviating Over-Smoothing via Aggregation over Compact Manifolds
To this end, we propose the aggregation over compacted manifolds method (ACM) that replaces the existing information aggregation with aggregation over compact manifolds, a special type of manifold, which avoids contracted aggregations.
COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing
Specifically, we propose an efficient sliding-window-based strategy to calculate the similarity among tokens in the diffusion features of source videos, identifying the tokens with high correspondence across frames.
Follow-Your-Pose v2: Multiple-Condition Guided Character Image Animation for Stable Pose Control
While existing character image animation methods using pose sequences and reference images have shown promising performance, they tend to struggle with incoherent animation in complex scenarios, such as multiple character animation and body occlusion.
Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation
We present Follow-Your-Emoji, a diffusion-based framework for portrait animation, which animates a reference portrait with target landmark sequences.
MultiBooth: Towards Generating All Your Concepts in an Image from Text
MultiBooth addresses these issues by dividing the multi-concept generation process into two phases: a single-concept learning phase and a multi-concept integration phase.
Heterogeneous Network Based Contrastive Learning Method for PolSAR Land Cover Classification
Besides, this work has implications for how to efficiently utilize the multi-features of PolSAR data to learn better high-level representation in CL and how to construct networks suitable for PolSAR data better.
Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts
Despite recent advances in image-to-video generation, better controllability and local animation are less explored.
SemanticSLAM: Learning based Semantic Map Construction and Robust Camera Localization
This approach enables the creation of a semantic map of the environment and ensures reliable camera localization.
M-BEV: Masked BEV Perception for Robust Autonomous Driving
It mimics various missing cases by randomly masking features of different camera views, then leverages the original features of these views as self-supervision, and reconstructs the masked ones with the distinct spatio-temporal context across views.
MagicScroll: Nontypical Aspect-Ratio Image Generation for Visual Storytelling via Multi-Layered Semantic-Aware Denoising
Visual storytelling often uses nontypical aspect-ratio images like scroll paintings, comic strips, and panoramas to create an expressive and compelling narrative.
MagicStick: Controllable Video Editing via Control Handle Transformations
Yet succinct, our method is the first method to show the ability of video property editing from the pre-trained text-to-image model.
Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection
Video Moment Retrieval (MR) and Highlight Detection (HD) have attracted significant attention due to the growing demand for video analysis.
Ranked #2 on
Highlight Detection
on YouTube Highlights
Efficient Computation of General Modules for ALC Ontologies (Extended Version)
Our evaluation indicates that our general modules are often smaller than classical modules and uniform interpolants computed by the state-of-the-art, and compared with uniform interpolants, can be computed in a significantly shorter time.
Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos
Generating text-editable and pose-controllable character videos have an imperious demand in creating various digital human.
SemanticAC: Semantics-Assisted Framework for Audio Classification
In this paper, we propose SemanticAC, a semantics-assisted framework for Audio Classification to better leverage the semantic information.
SimVTP: Simple Video Text Pre-training with Masked Autoencoders
This paper presents SimVTP: a Simple Video-Text Pretraining framework via masked autoencoders.
Ranked #24 on
Moment Retrieval
on Charades-STA
A Meta Path Based Evaluation Method for Enterprise Credit Risk
Nowadays small and medium-sized enterprises have become an essential part of the national economy.
Union and Intersection of all Justifications
We present new algorithm for computing the union and intersection of all justifications for a given ontological consequence without first computing the set of all justifications.
Self-semi-supervised Learning to Learn from NoisyLabeled Data
The remarkable success of today's deep neural networks highly depends on a massive number of correctly labeled data.
An End-to-End Dialogue State Tracking System with Machine Reading Comprehension and Wide & Deep Classification
This paper describes our approach in DSTC 8 Track 4: Schema-Guided Dialogue State Tracking.
How to Pre-Train Your Model? Comparison of Different Pre-Training Models for Biomedical Question Answering
We find open domain question answering model to be a better fit for this task rather than reading comprehension model.
Cascaded LSTMs based Deep Reinforcement Learning for Goal-driven Dialogue
Dialogue embeddings are learned by a LSTM at the middle of the network, and updated by the feeding of all turn embeddings.
An Adaption of BIOASQ Question Answering dataset for Machine Reading systems by Manual Annotations of Answer Spans.
BIOASQ Task B Phase B challenge focuses on extracting answers from snippets for a given question.
On the measure of conflicts: A MUS-Decomposition Based Framework
One particular MUS-decomposition, named distributable MUS-decomposition leads to an interesting partition of inconsistencies in a knowledge base such that multiple experts can check inconsistencies in parallel, which is impossible under existing measures.
A Distance-based Paraconsistent Semantics for DL-Lite
DL-Lite is an important family of description logics.
