Search Results for author:
Found 19 papers, 7 papers with code
MTL-SLT: Multi-Task Learning for Spoken Language Tasks
The proposed framework benefits from three key aspects: 1) pre-trained sub-networks of ASR model and language model; 2) multi-task learning objective to exploit shared knowledge from different tasks; 3) end-to-end training of ASR and downstream NLP task based on sequence loss.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
BMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation
We propose a novel deep-learning-based video interpolation algorithm based on bilateral motion estimation.
Ranked #15 on
Video Frame Interpolation
on MSU Video Frame Interpolation
(PSNR metric)
Harmonic (Quantum) Neural Networks
In this work, we derive exactly-harmonic (conventional- and quantum-) neural networks in two dimensions for simply-connected domains by leveraging the characteristics of holomorphic complex functions.
Exposure-Aware Dynamic Weighted Learning for Single-Shot HDR Imaging
We propose a novel single-shot high dynamic range (HDR) imaging algorithm based on exposure-aware dynamic weighted learning, which reconstructs an HDR image from a spatially varying exposure (SVE) raw image.
Depth Map Decomposition for Monocular Depth Estimation
We propose a novel algorithm for monocular depth estimation that decomposes a metric depth map into a normalized depth map and scale features.
Ranked #17 on
Monocular Depth Estimation
on NYU-Depth V2
(using extra training data)
QbyE-MLPMixer: Query-by-Example Open-Vocabulary Keyword Spotting using MLPMixer
Current keyword spotting systems are typically trained with a large amount of pre-defined keywords.
NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results
The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i. e. solutions can not exceed a given number of operations).
openFEAT: Improving Speaker Identification by Open-set Few-shot Embedding Adaptation with Transformer
Household speaker identification with few enrollment utterances is an important yet challenging problem, especially when household members share similar voice characteristics and room acoustics.
Asymmetric Bilateral Motion Estimation for Video Frame Interpolation
First, we predict symmetric bilateral motion fields to interpolate an anchor frame.
Ranked #6 on
Video Frame Interpolation
on MSU Video Frame Interpolation
(VMAF metric)
On joint training with interfaces for spoken language understanding
Spoken language understanding (SLU) systems extract both text transcripts and semantics associated with intents and slots from input speech utterances.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
End-to-end Neural Diarization: From Transformer to Conformer
We propose a new end-to-end neural diarization (EEND) system that is based on Conformer, a recently proposed neural architecture that combines convolutional mappings and Transformer to model both local and global dependencies in speech.
Learning Multiple Pixelwise Tasks Based on Loss Scale Balancing
We propose a novel loss weighting algorithm, called loss scale balancing (LSB), for multi-task learning (MTL) of pixelwise vision tasks.
BW-EDA-EEND: Streaming End-to-End Neural Speaker Diarization for a Variable Number of Speakers
We present a novel online end-to-end neural diarization system, BW-EDA-EEND, that processes data incrementally for a variable number of speakers.
BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation
We propose a novel deep-learning-based video interpolation algorithm based on bilateral motion estimation.
Ranked #3 on
Video Frame Interpolation
on Middlebury
NTIRE 2020 Challenge on Image Demoireing: Methods and Results
Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image.
Cross-modal Learning for Multi-modal Video Categorization
Multi-modal machine learning (ML) models can process data in multiple modalities (e. g., video, audio, text) and are useful for video content analysis in a variety of problems (e. g., object detection, scene understanding, activity recognition).
Exploiting Temporal Coherence for Multi-modal Video Categorization
Multimodal ML models can process data in multiple modalities (e. g., video, images, audio, text) and are useful for video content analysis in a variety of problems (e. g., object detection, scene understanding).
Semantic Line Detection and Its Applications
Then, we develop the line pooling layer to extract a feature vector for each candidate line from the feature maps.
Ranked #3 on
Line Detection
on SEL
A Maximum A Posteriori Estimation Framework for Robust High Dynamic Range Video Synthesis
For HDR video, a stiff practical challenge presents itself in the form of accurate correspondence estimation of objects between video frames.
