Search Results for author:
Found 21 papers, 17 papers with code
SF-Loc: A Visual Mapping and Geo-Localization System based on Sparse Visual Structure Frames
For high-level geo-spatial applications and intelligent robotics, accurate global pose information is of crucial importance.
Reliable and diverse evaluation of LLM medical knowledge mastery
Finally, these produced predicate variants are converted into textual language, resulting in a series of reliable and diverse test samples to evaluate whether LLMs fully master the given medical factual knowledge point.
Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation
Sampling-based decoding strategies have been widely adopted for Large Language Models (LLMs) in numerous applications, which target a balance between diversity and quality via temperature tuning and tail truncation (e. g., top-k and top-p sampling).
Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
Vision-and-Language Navigation (VLN) aims to develop embodied agents that navigate based on human instructions.
MultifacetEval: Multifaceted Evaluation to Probe LLMs in Mastering Medical Knowledge
In this paper, we aim to explore the causes of this gap by employing a multifaceted examination schema to systematically probe the actual mastery of medical knowledge by current LLMs.
MultiMax: Sparse and Multi-Modal Attention Learning
Yet, as a smooth approximation to the Argmax function, a significant amount of probability mass is distributed to other, residual entries, leading to poor interpretability and noise.
DBA-Fusion: Tightly Integrating Deep Dense Visual Bundle Adjustment with Multiple Sensors for Large-Scale Localization and Mapping
Visual simultaneous localization and mapping (VSLAM) has broad applications, with state-of-the-art methods leveraging deep neural networks for better robustness and applicability.
BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition
To remedy this we propose a two-fold strategy: (1) We introduce an innovative approach that encodes bone connectivity by harnessing the power of graph distances to describe the physical topology; we further incorporate action-specific topological representation via persistent homology analysis to depict systemic dynamics.
Ranked #6 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Dynamic multi-graph neural network for traffic flow prediction incorporating traffic accidents
Second, we designed a dynamic graph adjustment module to update the adjacency matrix used in each training step.
BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics
We further provide a strong baseline method, BOTH2Hands, for the novel task: generating vivid two-hand motions from both implicit body dynamics and explicit text prompts.
Recognition-Guided Diffusion Model for Scene Text Image Super-Resolution
Scene Text Image Super-Resolution (STISR) aims to enhance the resolution and legibility of text within low-resolution (LR) images, consequently elevating recognition accuracy in Scene Text Recognition (STR).
DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services
We propose DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services.
Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition
We propose a method specifically designed for hand action recognition which uses relative angular embeddings and local Spherical Harmonics to create novel hand representations.
THiFLY Research at SemEval-2023 Task 7: A Multi-granularity System for CTR-based Textual Entailment and Evidence Retrieval
The NLI4CT task aims to entail hypotheses based on Clinical Trial Reports (CTRs) and retrieve the corresponding evidence supporting the justification.
Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness
As a remedy, we propose a threefold strategy: (1) We forge an innovative pathway that encodes bone connectivity by harnessing the power of graph distances.
Hypergraph Transformer for Skeleton-based Action Recognition
Skeleton-based action recognition aims to recognize human actions given human joint coordinates with skeletal interconnections.
Ranked #12 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Generative Action Description Prompts for Skeleton-based Action Recognition
More specifically, we employ a pre-trained large-scale language model as the knowledge engine to automatically generate text descriptions for body parts movements of actions, and propose a multi-modal training scheme by utilizing the text encoder to generate feature vectors for different body parts and supervise the skeleton encoder for action representation learning.
Ranked #7 on
Skeleton Based Action Recognition
on N-UCLA
SP-ViT: Learning 2D Spatial Priors for Vision Transformers
Unlike convolutional inductive biases, which are forced to focus exclusively on hard-coded local regions, our proposed SPs are learned by the model itself and take a variety of spatial relations into account.
Ranked #162 on
Image Classification
on ImageNet
Table-based Fact Verification with Self-adaptive Mixture of Experts
The table-based fact verification task has recently gained widespread attention and yet remains to be a very challenging problem.
THiFly\_Queens at SemEval-2021 Task 9: Two-stage Statement Verification with Adaptive Ensembling and Slot-based Operation
This paper describes our system for verifying statements with tables at SemEval-2021 Task 9.
Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features
We refine previous investigations of this failure at anomaly detection for invertible generative networks and provide a clear explanation of it as a combination of model bias and domain prior: Convolutional networks learn similar low-level feature distributions when trained on any natural image dataset and these low-level features dominate the likelihood.
