Search Results for author:
Found 29 papers, 6 papers with code
Acoustic Neural 3D Reconstruction Under Pose Drift
We consider the problem of optimizing neural implicit surfaces for 3D reconstruction using acoustic images collected with drifting sensor poses.
MedicalNarratives: Connecting Medical Vision and Language with Localized Narratives
We propose MedicalNarratives, a dataset curated from medical pedagogical videos similar in nature to data collected in Think-Aloud studies and inspired by Localized Narratives, which collects grounded image-text data by curating instructors' speech and mouse cursor movements synchronized in time.
MaDCoW: Marginal Distortion Correction for Wide-Angle Photography with Arbitrary Objects
We introduce MaDCoW, a method for correcting marginal distortion of arbitrary objects in wide-angle photography.
SCBench: A Sports Commentary Benchmark for Video LLMs
Inspired by these challenges, we propose a novel task: sports video commentary generation, developed $\textbf{SCBench}$ for Video LLMs.
Aligning AI-driven discovery with human intuition
We propose a new general principle for distilling representations that are naturally more aligned with human intuition, without relying on prior physical knowledge.
Using Deep Autoregressive Models as Causal Inference Engines
We propose an autoregressive (AR) CI framework capable of handling complex confounders and sequential actions common in modern applications.
CaBaGe: Data-Free Model Extraction using ClAss BAlanced Generator Ensemble
Machine Learning as a Service (MLaaS) is often provided as a pay-per-query, black-box system to clients.
MR-MLLM: Mutual Reinforcement of Multimodal Comprehension and Vision Perception
In recent years, multimodal large language models (MLLMs) have shown remarkable capabilities in tasks like visual question answering and common sense reasoning, while visual perception models have made significant strides in perception tasks, such as detection and segmentation.
Conformer-1: Robust ASR via Large-Scale Semisupervised Bootstrapping
This paper presents Conformer-1, an end-to-end Automatic Speech Recognition (ASR) model trained on an extensive dataset of 570k hours of speech audio data, 91% of which was acquired from publicly available sources.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Z-Splat: Z-Axis Gaussian Splatting for Camera-Sonar Fusion
In this manuscript, we demonstrate that using transient data (from sonars) allows us to address the missing cone problem by sampling high-frequency data along the depth axis.
Self-Healing Effects in OAM Beams Observed on a 28 GHz Experimental Link
The OAM beams have a helical phase and polarization structure and have conical amplitude shape in the far field.
AONeuS: A Neural Rendering Framework for Acoustic-Optical Sensor Fusion
Underwater perception and 3D surface reconstruction are challenging problems with broad applications in construction, security, marine archaeology, and environmental monitoring.
Cloud-Device Collaborative Learning for Multimodal Large Language Models
However, the deployment of these large-scale MLLMs on client devices is hindered by their extensive model parameters, leading to a notable decline in generalization capabilities when these models are compressed for device deployment.
ConVRT: Consistent Video Restoration Through Turbulence with Test-time Optimization of Neural Video Representations
tmospheric turbulence presents a significant challenge in long-range imaging.
A Scalable Training Strategy for Blind Multi-Distribution Noise Removal
Our work improves upon a recently proposed universal denoiser training strategy by extending these results to higher dimensions and by incorporating a polynomial approximation of the true specification-loss landscape.
Seeing the World through Your Eyes
The reflective nature of the human eye is an underappreciated source of information about what the world around us looks like.
Machine learning reveals features of spinon Fermi surface
With rapid progress in simulation of strongly interacting quantum Hamiltonians, the challenge in characterizing unknown phases becomes a bottleneck for scientific progress.
G-MATT: Single-step Retrosynthesis Prediction using Molecular Grammar Tree Transformer
Additional analyses of G-MATT attention maps demonstrate the ability to retain chemistry knowledge without relying on excessively complex model architectures.
PAniC-3D: Stylized Single-view 3D Reconstruction from Portraits of Anime Characters
We propose PAniC-3D, a system to reconstruct stylized 3D character heads directly from illustrated (p)ortraits of (ani)me (c)haracters.
PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection
Masked Autoencoders learn strong visual representations and achieve state-of-the-art results in several independent modalities, yet very few works have addressed their capabilities in multi-modality settings.
T-SEA: Transfer-based Self-Ensemble Attack on Object Detection
Then, we analogize patch optimization with regular model optimization, proposing a series of self-ensemble approaches on the input data, the attacked model, and the adversarial patch to efficiently make use of the limited information and prevent the patch from overfitting.
i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?
(2) Whether we can enhance the representations in the latent feature space by controlling the degree of semantics during sampling on Masked Autoencoders?
MetaDIP: Accelerating Deep Image Prior with Meta Learning
Deep image prior (DIP) is a recently proposed technique for solving imaging inverse problems by fitting the reconstructed images to the output of an untrained convolutional neural network.
Sequential Models in the Synthetic Data Vault
After building the Sequential SDV, we used it to generate synthetic data and compared its quality against an existing, non-sequential generative adversarial network based model called CTGAN.
Memory-efficient Learning for High-Dimensional MRI Reconstruction
Deep learning (DL) based unrolled reconstructions have shown state-of-the-art performance for under-sampled magnetic resonance imaging (MRI).
Fomite transmission and disinfection strategies for SARS-CoV-2 and related viruses
Contaminated objects or surfaces, referred to as fomites, play a critical role in the spread of viruses, including SARS-CoV-2, the virus responsible for the COVID-19 pandemic.
Memory-efficient Learning for Large-scale Computational Imaging
Critical aspects of computational imaging systems, such as experimental design and image priors, can be optimized through deep networks formed by the unrolled iterations of classical model-based reconstructions (termed physics-based networks).
Leveraging Multimodal Haptic Sensory Data for Robust Cutting
In this paper, we propose using vibrations and force-torque feedback from the interactions to adapt the slicing motions and monitor for contact events.
Double Anchor R-CNN for Human Detection in a Crowd
Double Anchor RPN is developed to capture body and head parts in pairs.
