Search Results for author:
Found 23 papers, 7 papers with code
Hierarchical Representation-based Dynamic Reasoning Network for Biomedical Question Answering
It then performs dynamic reasoning based on the hierarchical representations of evidences to solve complex biomedical problems.
Exploring the Role of Explicit Temporal Modeling in Multimodal Large Language Models for Video Understanding
Using STE, we systematically compare implicit and explicit temporal modeling across dimensions such as overall performance, token compression effectiveness, and temporal-specific understanding.
Evaluating and Advancing Multimodal Large Language Models in Ability Lens
To address this, we introduce \textbf{AbilityLens}, a unified benchmark designed to evaluate MLLMs across six key perception abilities, focusing on both accuracy and stability, with each ability encompassing diverse question types, domains, and metrics.
USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting
Leveraging the multi-view consistency afforded by 3DGS and the motion capture capability of the spike camera, our framework enables a joint iterative optimization that seamlessly integrates information between the spike-to-image network and 3DGS.
Effectively Enhancing Vision Language Large Models by Prompt Augmentation and Caption Utilization
may change model output and make the output hallucinate again.
SpikeGS: 3D Gaussian Splatting from Spike Streams with High-Speed Camera Motion
To address this issue, we make the first attempt to introduce the 3D Gaussian Splatting (3DGS) into spike cameras in high-speed capture, providing 3DGS as dense and continuous clues of views, then constructing SpikeGS.
SpikeMM: Flexi-Magnification of High-Speed Micro-Motions
This innovative approach comprehensively records temporal and spatial visual information, rendering it particularly suitable for magnifying high-speed micro-motions. This paper introduces SpikeMM, a pioneering spike-based algorithm tailored specifically for high-speed motion magnification.
SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams
Our approach begins with the formulation of a spike-guided deblurring model that explores the theoretical relationships among spike streams, blurry images, and their corresponding sharp sequences.
Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment
It can supplement the temporal information lost in traditional cameras and guide motion deblurring.
CIEM: Contrastive Instruction Evaluation Method for Better Instruction Tuning
Nowadays, the research on Large Vision-Language Models (LVLMs) has been significantly promoted thanks to the success of Large Language Models (LLM).
Unveiling the Potential of Spike Streams for Foreground Occlusion Removal from Densely Continuous Views
To process the spikes, we build a novel model \textbf{SpkOccNet}, in which we integrate information of spikes from continuous viewpoints within multi-windows, and propose a novel cross-view mutual attention mechanism for effective fusion and refinement.
Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios
Based on this, we propose Asymmetric Tunable Blind-Spot Network (AT-BSN), where the blind-spot size can be freely adjusted, thus better balancing noise correlation suppression and image local spatial destruction during training and inference.
SpikeCV: Open a Continuous Computer Vision Era
SpikeCV focuses on encapsulation for spike data, standardization for dataset interfaces, modularization for vision tasks, and real-time applications for challenging scenes.
Uncertainty Guided Depth Fusion for Spike Camera
In this paper, we propose a novel Uncertainty-Guided Depth Fusion (UGDF) framework to fuse the predictions of monocular and stereo depth estimation networks for spike camera.
Mixture of Experts for Biomedical Question Answering
In this paper, in order to alleviate the parameter competition problem, we propose a Mixture-of-Expert (MoE) based question answering method called MoEBQA that decouples the computation for different types of questions by sparse routing.
A Deep Learning Inference Scheme Based on Pipelined Matrix Multiplication Acceleration Design and Non-uniform Quantization
Matrix multiplication is the bedrock in Deep Learning inference application.
Accelerating Training of Deep Spiking Neural Networks with Parameter Initialization
Despite that spiking neural networks (SNNs) show strong advantages in information encoding, power consuming, and computational capability, the underdevelopment of supervised learning algorithms is still a hindrance for training SNN.
Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation
Recently, many deep learning methods have shown great success in providing promising solutions to many event-based problems, such as optical flow estimation.
Cyclic Pólya Ensembles on the Unitary Matrices and their Spectral Statistics
The framework of spherical transforms and P\'olya ensembles is of utility in deriving structured analytic results for sums and products of random matrices in a unified way.
Point Processes
Probability
Mathematical Physics
Classical Analysis and ODEs
Mathematical Physics
60B20, 15B52, 43A85, 43A90
ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection
In this paper, we propose Virtual Pooling (ViP), a model-level approach to improve speed and energy consumption of CNN-based image classification and object detection tasks, with a provable error bound.
Memory-Attended Recurrent Network for Video Captioning
Typical techniques for video captioning follow the encoder-decoder framework, which can only focus on one source video being processed.
Chinese Poetry Generation with Flexible Styles
Research has shown that sequence-to-sequence neural models, particularly those with the attention mechanism, can successfully generate classical Chinese poems.
Flexible and Creative Chinese Poetry Generation Using Neural Memory
It has been shown that Chinese poems can be successfully generated by sequence-to-sequence neural models, particularly with the attention mechanism.
