Search Results for author:
Found 31 papers, 7 papers with code
RhyRNN: Rhythmic RNN for Recognizing Events in Long and Complex Videos
We study the behavior of RhyRNN and empirically show that our method works well even when mph{only event-level labels are available} in the training stage (compared to algorithms requiring sub-activity labels for recognition), and thus is more practical when the sub-activity labels are missing or difficult to obtain.
Dependency-aware Prototype Learning for Few-shot Relation Classification
This paper presents a novel dependency-aware prototype learning (DAPL) method for few-shot relation classification.
On Diffusion Process in SE(3)-invariant Space
Sampling viable 3D structures (e. g., molecules and point clouds) with SE(3)-invariance using diffusion-based models proved promising in a variety of real-world applications, wherein SE(3)-invariant properties can be naturally characterized by the inter-point distance manifold.
Graph Learning with Distributional Edge Layouts
Graph Neural Networks (GNNs) learn from graph-structured data by passing local messages between neighboring nodes along edges on certain topological layouts.
Boosting Graph Pooling with Persistent Homology
Recently, there has been an emerging trend to integrate persistent homology (PH) into graph neural networks (GNNs) to enrich expressive power.
Towards Principled Task Grouping for Multi-Task Learning
This paper presents a novel approach to task grouping in Multitask Learning (MTL), advancing beyond existing methods by addressing key theoretical and practical limitations.
Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theory
This paper presents a novel study of the oversmoothing issue in diffusion-based Graph Neural Networks (GNNs).
Constructive Large Language Models Alignment with Diverse Feedback
This limitation leads to suboptimal performance, even when ample training data is available.
Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis
Though Multimodal Sentiment Analysis (MSA) proves effective by utilizing rich information from multiple sources (e. g., language, video, and audio), the potential sentiment-irrelevant and conflicting information across modalities may hinder the performance from being further improved.
Ranked #1 on
Multimodal Sentiment Analysis
on CMU-MOSEI
(Acc-7 metric)
On Accelerating Diffusion-based Molecular Conformation Generation in SE(3)-invariant Space
Diffusion-based generative models in SE(3)-invariant space have demonstrated promising performance in molecular conformation generation, but typically require solving stochastic differential equations (SDEs) with thousands of update steps.
Molecular Conformation Generation via Shifting Scores
Molecular conformation generation, a critical aspect of computational chemistry, involves producing the three-dimensional conformer geometry for a given molecule.
A Hierarchical Destroy and Repair Approach for Solving Very Large-Scale Travelling Salesman Problem
Fair comparisons based on nineteen famous large-scale instances (with 10, 000 to 10, 000, 000 cities) show that HDR is highly competitive against existing state-of-the-art TSP algorithms, in terms of both efficiency and solution quality.
Towards Unbalanced Motion: Part-Decoupling Network for Video Portrait Segmentation
That is, motion of different parts of the portraits is unbalanced.
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
In this paper, we propose Speech-text dialog Pre-training for spoken dialog understanding with ExpliCiT cRoss-Modal Alignment (SPECTRA), which is the first-ever speech-text dialog pre-training model.
Ranked #1 on
Multimodal Sentiment Analysis
on MOSI
Emotion Recognition in Conversation
Multimodal Intent Recognition
+1
Efficient Training of Multi-task Combinarotial Neural Solver with Multi-armed Bandits
Efficiently training a multi-task neural solver for various combinatorial optimization problems (COPs) has been less studied so far.
ASP: Learn a Universal Neural Solver!
Applying machine learning to combinatorial optimization problems has the potential to improve both efficiency and accuracy.
Learning to Decouple Complex Systems
In this paper, we propose a sequential learning approach under this setting by decoupling a complex system for handling irregularly sampled and cluttered sequential observations.
W2SAT: Learning to generate SAT instances from Weighted Literal Incidence Graphs
The Boolean Satisfiability (SAT) problem stands out as an attractive NP-complete problem in theoretic computer science and plays a central role in a broad spectrum of computing-related applications.
Edge Rewiring Goes Neural: Boosting Network Resilience without Rich Features
In this case, GNNs can barely learn useful information, resulting in prohibitive difficulty in making actions for successively rewiring edges under a reinforcement learning context.
Learning Latent Topology for Graph Matching
Graph matching (GM) has been traditionally modeled as a deterministic optimization problem characterized by an affinity matrix under pre-defined graph topology.
Combinatorial Learning of Graph Edit Distance via Dynamic Embedding
This paper presents a hybrid approach by combing the interpretability of traditional search-based techniques for producing the edit path, as well as the efficiency and adaptivity of deep embedding models to achieve a cost-effective GED solver.
Determinant Regularization for Gradient-Efficient Graph Matching
Graph matching refers to finding vertex correspondence for a pair of graphs, which plays a fundamental role in many vision and learning related tasks.
Deep Learning of Determinantal Point Processes via Proper Spectral Sub-gradient
Determinantal point processes (DPPs) is an effective tool to deliver diversity on multiple machine learning and computer vision tasks.
Recognizing Video Events with Varying Rhythms
In this paper, we investigate the problem of recognizing long and complex events with varying action rhythms, which has not been considered in the literature but is a practical challenge.
Learning deep graph matching with channel-independent embedding and Hungarian attention
Graph matching aims to establishing node-wise correspondence between two graphs, which is a classic combinatorial problem and in general NP-complete.
Ranked #15 on
Graph Matching
on PASCAL VOC
(matching accuracy metric)
Plan-Recognition-Driven Attention Modeling for Visual Recognition
We build an event recognition system, ER-PRN, which takes Pixel Dynamics Network as a subroutine, to recognize events based on observations augmented by plan-recognition-driven attention.
Generalizing Graph Matching beyond Quadratic Assignment Model
Graph matching has received persistent attention over decades, which can be formulated as a quadratic assignment problem (QAP).
Incremental Multi-graph Matching via Diversity and Randomness based Graph Clustering
In this paper, we present an incremental multi-graph matching approach, which deals with the arriving graph utilizing the previous matching results under the global consistency constraint.
Weakly Supervised Attention Learning for Textual Phrases Grounding
Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction.
Joint Cuts and Matching of Partitions in One Graph
As two fundamental problems, graph cuts and graph matching have been investigated over decades, resulting in vast literature in these two topics respectively.
