Search Results for author:
Found 29 papers, 8 papers with code
EffLoc: Lightweight Vision Transformer for Efficient 6-DOF Camera Relocalization
Camera relocalization is pivotal in computer vision, with applications in AR, drones, robotics, and autonomous driving.
MLLMReID: Multimodal Large Language Model-based Person Re-identification
This paper will investigate how to adapt them for the task of ReID.
VLAP: Efficient Video-Language Alignment via Frame Prompting and Distilling for Video Question Answering
Our VLAP model addresses both efficient frame sampling and effective cross-modal alignment in a unified way.
Ranked #1 on
Video Question Answering
on STAR Benchmark
MeSa: Masked, Geometric, and Supervised Pre-training for Monocular Depth Estimation
Furthermore, via experiments on the NYUv2 and IBims-1 datasets, we demonstrate that these enhanced representations translate to performance improvements in both the in-distribution and out-of-distribution settings.
Ranked #10 on
Monocular Depth Estimation
on NYU-Depth V2
ICAR: Image-based Complementary Auto Reasoning
Based on this notion, we propose a compatibility learning framework, a category-aware Flexible Bidirectional Transformer (FBT), for visual "scene-based set compatibility reasoning" with the cross-domain visual similarity input and auto-regressive complementary item generation.
RoSI: Recovering 3D Shape Interiors from Few Articulation Images
The dominant majority of 3D models that appear in gaming, VR/AR, and those we use to train geometric deep learning algorithms are incomplete, since they are modeled as surface meshes and missing their interior structures.
Local-to-Global Panorama Inpainting for Locale-Aware Indoor Lighting Prediction
Recent methods mostly rely on convolutional neural networks (CNNs) to fill the missing contents in the warped panorama.
Aligning Multi-Sequence CMR Towards Fully Automated Myocardial Pathology Segmentation
For instance, balanced steady-state free precession cine sequences present clear anatomical boundaries, while late gadolinium enhancement and T2-weighted CMR sequences visualize myocardial scar and edema of MI, respectively.
MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images
We therefore conducted extensive experiments to investigate the performance of the proposed method in dealing with such complex combinations of different CMR sequences.
TotalSegmentator: robust segmentation of 104 anatomical structures in CT images
The model significantly outperformed another publicly available segmentation model on a separate dataset (Dice score, 0. 932 versus 0. 871, respectively).
End-to-End Voice Conversion with Information Perturbation
The ideal goal of voice conversion is to convert the source speaker's speech to sound naturally like the target speaker while maintaining the linguistic content and the prosody of the source speech.
VCVTS: Multi-speaker Video-to-Speech synthesis via cross-modal knowledge transfer from voice conversion
Though significant progress has been made for speaker-dependent Video-to-Speech (VTS) synthesis, little attention is devoted to multi-speaker VTS that can map silent video to speech, while allowing flexible control of speaker identity, all in a single system.
Deep Graph Learning for Spatially-Varying Indoor Lighting Prediction
At its core is a new lighting model (dubbed DSGLight) based on depth-augmented Spherical Gaussians (SG) and a Graph Convolutional Network (GCN) that infers the new lighting representation from a single LDR image of limited field-of-view.
A Color Image Steganography Based on Frequency Sub-band Selection
Color image steganography based on deep learning is the art of hiding information in the color image.
Referee: Towards reference-free cross-speaker style transfer with low-quality data for expressive speech synthesis
The S2W model is trained with high-quality target data, which is adopted to effectively aggregate style descriptors and generate high-fidelity speech in the target speaker's voice.
Attention Bottlenecks for Multimodal Fusion
Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio.
Ranked #2 on
Action Classification
on Kinetics-Sounds
Glow-WaveGAN: Learning Speech Representations from GAN-based Variational Auto-Encoder For High Fidelity Flow-based Speech Synthesis
Current two-stage TTS framework typically integrates an acoustic model with a vocoder -- the acoustic model predicts a low resolution intermediate representation such as Mel-spectrum while the vocoder generates waveform from the intermediate representation.
Controllable Context-aware Conversational Speech Synthesis
Specifically, we use explicit labels to represent two typical spontaneous behaviors filled-pause and prolongation in the acoustic model and develop a neural network based predictor to predict the occurrences of the two behaviors from text.
GLAVNet: Global-Local Audio-Visual Cues for Fine-Grained Material Recognition
We demonstrate that local geometry has a greater impact on the sound than the global geometry and offers more cues in material recognition.
Optical Mouse: 3D Mouse Pose From Single-View Video
We present a method to infer the 3D pose of mice, including the limbs and feet, from monocular videos.
Entity Concept-enhanced Few-shot Relation Extraction
Few-shot relation extraction (FSRE) is of great importance in long-tail distribution problem, especially in special domain with low-resource data.
AI Choreographer: Music Conditioned 3D Dance Generation with AIST++
We present AIST++, a new multi-modal dataset of 3D dance motion and music, along with FACT, a Full-Attention Cross-modal Transformer network for generating 3D dance motion conditioned on music.
Ranked #2 on
Motion Synthesis
on BRACE
Phonetic Posteriorgrams based Many-to-Many Singing Voice Conversion via Adversarial Training
In order to make timbre conversion more stable and controllable, speaker embedding is further decomposed to the weighted sum of a group of trainable vectors representing different timbre clusters.
Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech
In this paper, we propose multi-band MelGAN, a much faster waveform generation model targeting to high-quality text-to-speech.
Sound Audio and Speech Processing
Adversarial Feature Learning and Unsupervised Clustering based Speech Synthesis for Found Data with Acoustic and Textual Noise
As for the speech-side noise, we propose to learn a noise-independent feature in the auto-regressive decoder through adversarial training and data augmentation, which does not need an extra speech enhancement model.
Learning-Based Cloth Material Recovery From Video
To extract information about the cloth, our method characterizes both the motion space and the visual appearance of the cloth geometry.
Statistical Parametric Speech Synthesis Using Generative Adversarial Networks Under A Multi-task Learning Framework
In this paper, we aim at improving the performance of synthesized speech in statistical parametric speech synthesis (SPSS) based on a generative adversarial network (GAN).
Sound
Detailed Garment Recovery from a Single-View Image
Most recent garment capturing techniques rely on acquiring multiple views of clothing, which may not always be readily available, especially in the case of pre-existing photographs from the web.
Modeling Context in Referring Expressions
Humans refer to objects in their environments all the time, especially in dialogue with other people.
