Search Results for author:
Found 25 papers, 12 papers with code
Super Encoding Network: Recursive Association of Multi-Modal Encoders for Video Understanding
To fill this gap, we propose a unified Super Encoding Network (SEN) for video understanding, which builds up such distinct interactions through recursive association of multi-modal encoders in the foundation models.
Blend the Separated: Mixture of Synergistic Experts for Data-Scarcity Drug-Target Interaction Prediction
Extensive experiments on 3 real-world datasets under different extents of input data scarcity and/or label scarcity demonstrate our model outperforms states of the art significantly and steadily, with a maximum improvement of 53. 53%.
LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents
In order to better address long video tasks, we introduce LVAgent, the first framework enabling multi-round dynamic collaboration of MLLM agents in long video understanding.
Computational Efficiency
Optical Character Recognition (OCR)
+2
Medical Image Quality Assessment based on Probability of Necessity and Sufficiency
To that end, we propose an MIQA framework based on a concept from causal inference: Probability of Necessity and Sufficiency (PNS).
Seeking the Sufficiency and Necessity Causal Features in Multimodal Representation Learning
We address these challenges by first conceptualizing multimodal representations as comprising modality-invariant and modality-specific components.
Advancing Cell Detection in Anterior Segment Optical Coherence Tomography Images
This framework consists of a zero-shot chamber segmentation module and a cell detection module.
JEN-1 DreamStyler: Customized Musical Concept Learning via Pivotal Parameters Tuning
In this paper, we propose a novel method for customized text-to-music generation, which can capture the concept from a two-minute reference music and generate a new piece of music conforming to the concept.
Percept, Chat, and then Adapt: Multimodal Knowledge Transfer of Foundation Models for Open-World Video Recognition
Finally, we blend external multimodal knowledge in Adapt stage, by inserting multimodal knowledge adaptation modules into networks.
JEN-1 Composer: A Unified Framework for High-Fidelity Multi-Track Music Generation
With rapid advances in generative artificial intelligence, the text-to-music synthesis task has emerged as a promising direction for music generation.
Ternary Singular Value Decomposition as a Better Parameterized Form in Linear Mapping
We present a simple yet novel parameterized form of linear mapping to achieves remarkable network compression performance: a pseudo SVD called Ternary SVD (TSVD).
JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models
Despite the task's significance, prevailing generative models exhibit limitations in music quality, computational efficiency, and generalization.
Ranked #5 on
Text-to-Music Generation
on MusicCaps
Modify Training Directions in Function Space to Reduce Generalization Error
We propose theoretical analyses of a modified natural gradient descent method in the neural network function space based on the eigendecompositions of neural tangent kernel and Fisher information matrix.
1st Place Solutions for the UVO Challenge 2022
This paper describes the approach we have taken in the challenge.
Low-Resolution Action Recognition for Tiny Actions Challenge
Second, these activities are naturally distributed in a long-tailed way.
FedDKD: Federated Learning with Decentralized Knowledge Distillation
The FedDKD introduces a module of decentralized knowledge distillation (DKD) to distill the knowledge of the local models to train the global model by approaching the neural network map average based on the metric of divergence defined in the loss function, other than only averaging parameters as done in literature.
Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking
Exploiting a general-purpose neural architecture to replace hand-wired designs or inductive biases has recently drawn extensive interest.
Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Network
However, succeeding researches pointed out that limited by the uncontrolled nature of attention computation, the NMT model requires an external syntax to capture the deep syntactic awareness.
BN-NAS: Neural Architecture Search with Batch Normalization
We present BN-NAS, neural architecture search with Batch Normalization (BN-NAS), to accelerate neural architecture search (NAS).
PSViT: Better Vision Transformer via Token Pooling and Attention Sharing
Then, a compact set of the possible combinations for different token pooling and attention sharing mechanisms are constructed.
GLiT: Neural Architecture Search for Global and Local Image Transformer
We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition.
Ranked #548 on
Image Classification
on ImageNet
Gaze Estimation with an Ensemble of Four Architectures
This paper presents a method for gaze estimation according to face images.
Evolving Search Space for Neural Architecture Search
The automation of neural architecture design has been a coveted alternative to human experts.
Real-time 'Actor-Critic' Tracking
In this work, we propose a novel tracking algorithm with real-time performance based on the âActor-Criticâ framework.
Meta-Learning with Hessian-Free Approach in Deep Neural Nets Training
Meta-learning is a promising method to achieve efficient training method towards deep neural net and has been attracting increases interests in recent years.
