Search Results for author:
Found 24 papers, 18 papers with code
VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning
Despite the advancements of Video Large Language Models (VideoLLMs) in various tasks, they struggle with fine-grained temporal understanding, such as Dense Video Captioning (DVC).
Difficulty-aware Balancing Margin Loss for Long-tailed Recognition
When trained with severely imbalanced data, deep neural networks often struggle to accurately recognize classes with only a few samples.
Inversion-based Latent Bayesian Optimization
LBO learns a surrogate model to approximate the black-box objective function in the latent space.
LLaMo: Large Language Model-based Molecular Graph Assistant
Thus, we propose LLaMo: Large Language Model-based Molecular graph assistant, which is an end-to-end trained large molecular graph-language model.
Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation
Knowledge graph-grounded dialog generation requires retrieving a dialog-relevant subgraph from the given knowledge base graph and integrating it with the dialog history.
Flow-Assisted Motion Learning Network for Weakly-Supervised Group Activity Recognition
The first pathway of the relation module, the actor-centric path, initially captures the temporal dynamics of individual actors and then constructs inter-actor relationships.
Prompt Learning via Meta-Regularization
Recently, prompt learning approaches have been explored to efficiently and effectively adapt the vision-language models to a variety of downstream tasks.
Ranked #4 on
Prompt Engineering
on UCF101
Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection
Groupwise Query Specialization trains a specialized query by dividing queries and relations into disjoint groups and directing a query in a specific query group solely toward relations in the corresponding relation group.
Ranked #1 on
Scene Graph Generation
on Visual Genome
Graph Elicitation for Guiding Multi-Step Reasoning in Large Language Models
To deal with them, we propose a GE-Reasoning method, which directs LLMs to generate proper sub-questions and corresponding answers.
Sketch-based Video Object Localization
We introduce Sketch-based Video Object Localization (SVOL), a new task aimed at localizing spatio-temporal object boxes in video queried by the input sketch.
Self-positioning Point-based Transformer for Point Cloud Understanding
In this paper, we present a Self-Positioning point-based Transformer (SPoTr), which is designed to capture both local and global shape contexts with reduced complexity.
Ranked #4 on
3D Part Segmentation
on ShapeNet-Part
RainUNet for Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts
This paper presents a solution to the Weather4cast 2022 Challenge Stage 2.
Relation-Aware Language-Graph Transformer for Question Answering
To address these issues, we propose Question Answering Transformer (QAT), which is designed to jointly reason over language and graphs with respect to entity relations in a unified manner.
Deformable Graph Transformer
Transformer-based models have recently shown success in representation learning on graph-structured data beyond natural language processing and computer vision.
Metropolis-Hastings Data Augmentation for Graph Neural Networks
We also propose a simple and effective semi-supervised learning strategy with generated samples from MH-Aug. Our extensive experiments demonstrate that MH-Aug can generate a sequence of samples according to the target distribution to significantly improve the performance of GNNs.
Explore-And-Match: Bridging Proposal-Based and Proposal-Free With Transformer for Sentence Grounding in Videos
To our surprise, we found that training schedule shows divide-and-conquer-like pattern: time segments are first diversified regardless of the target, then coupled with each target, and fine-tuned to the target again.
Deformable Graph Convolutional Networks
To address the two common problems of graph convolution, in this paper, we propose Deformable Graph Convolutional Networks (Deformable GCNs) that adaptively perform convolution in multiple latent spaces and capture short/long-range dependencies between nodes.
Ranked #3 on
Node Classification on Non-Homophilic (Heterophilic) Graphs
on Cornell (48%/32%/20% fixed splits)
Node Classification on Non-Homophilic (Heterophilic) Graphs
Representation Learning
OCR-free Document Understanding Transformer
Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs.
Ranked #7 on
Key-value Pair Extraction
on SIBR
Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
Our method is learning to learn a primary task with various auxiliary tasks to improve generalization performance.
Deep neural network for solving differential equations motivated by Legendre-Galerkin approximation
Nonlinear differential equations are challenging to solve numerically and are important to understanding the dynamics of many physical systems.
Robust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methods
Motivated by the SSP property and a generalized Runge-Kutta method, we propose Strong Stability Preserving networks (SSP networks) which improve robustness against adversarial attacks.
Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
Our proposed method is learning to learn a primary task by predicting meta-paths as auxiliary tasks.
The number of maximal independent sets in the Hamming cube
Let $Q_n$ be the $n$-dimensional Hamming cube and $N=2^n$.
Combinatorics 05C69
