Search Results for author:
Found 27 papers, 12 papers with code
SPICED: News Similarity Detection Dataset with Multiple Topics and Complexity Levels
Nowadays, the use of intelligent systems to detect redundant information in news articles has become especially prevalent with the proliferation of news media outlets in order to enhance user experience.
MagicProp: Diffusion-based Video Editing via Motion-aware Appearance Propagation
The flexibility of these techniques enables the editing of arbitrary regions within the frame.
Enhancing conversational quality in language learning chatbots: An evaluation of GPT4 for ASR error correction
The integration of natural language processing (NLP) technologies into educational applications has shown promising results, particularly in the language learning domain.
Unsupervised domain adaptation for speech recognition with unsupervised error correction
The transcription quality of automatic speech recognition (ASR) systems degrades significantly when transcribing audios coming from unseen domains.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Motion-Adjustable Neural Implicit Video Representation
The model is trained end-to-end on a video to jointly determine the phase-shift values at each time with the mapping from the phase-shifted sinusoidal functions to the corresponding frame, enabling an implicit video representation.
Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?
We find two reasons why IM is not better than LOO: (1) deleting a single word from the input only marginally reduces a classifier's accuracy; and (2) a highly predictable word is always given near-zero attribution, regardless of its true importance to the classifier.
Compositional Sketch Search
We present an algorithm for searching image collections using free-hand sketches that describe the appearance and relative positions of multiple objects.
APES: Audiovisual Person Search in Untrimmed Video
To showcase the potential of our new dataset, we propose an audiovisual baseline and benchmark for person retrieval.
Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging
Neural networks have shown great abilities in estimating depth from a single image.
Ranked #1 on
Monocular Depth Estimation
on Middlebury 2014
Out of Order: How Important Is The Sequential Order of Words in a Sentence in Natural Language Understanding Tasks?
Encouraging classifiers to capture word order information improves the performance on most GLUE tasks, SQuAD 2. 0 and out-of-samples.
Natural Language Inference
Natural Language Understanding
+2
Learning to Recover 3D Scene Shape from a Single Image
Despite significant progress in monocular depth estimation in the wild, recent state-of-the-art methods cannot be used to recover accurate 3D scene shape due to an unknown depth shift induced by shift-invariant reconstruction losses used in mixed-data depth prediction training, and possible unknown camera focal length.
Ranked #1 on
Indoor Monocular Depth Estimation
on DIODE
(using extra training data)
Revisiting Adaptive Convolutions for Video Frame Interpolation
Video frame interpolation, the synthesis of novel views in time, is an increasingly popular research direction with many new papers further advancing the state of the art.
Active Speakers in Context
Current methods for active speak er detection focus on modeling short-term audiovisual information from a single speaker.
Context-Aware Group Captioning via Self-Attention and Contrastive Features
In this paper, we introduce a new task, context-aware group captioning, which aims to describe a group of target images in the context of another group of related reference images.
BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images
Our experiments show that using explicit 3D features to represent objects allows BlockGAN to learn disentangled representations both in terms of objects (foreground and background) and their properties (pose and identity).
A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings
Large, pre-trained generative models have been increasingly popular and useful to both the research and wider communities.
An Internal Learning Approach to Video Inpainting
We propose a novel video inpainting algorithm that simultaneously hallucinates missing appearance and motion (optical flow) information, building upon the recent 'Deep Image Prior' (DIP) that exploits convolutional network architectures to enforce plausible texture in static images.
3D Ken Burns Effect from a Single Image
According to this depth estimate, our framework then maps the input image to a point cloud and synthesizes the resulting video frames by rendering the point cloud from the corresponding camera positions.
Ranked #4 on
Depth Estimation
on NYU-Depth V2
M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning
Instead of sequentially distilling knowledge only from the last model, we directly leverage all previous model snapshots.
Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects
Using our framework and a self-assembled dataset of 3D objects, we investigate the vulnerability of DNNs to OoD poses of well-known objects in ImageNet.
Interactive Boundary Prediction for Object Selection
Instead of relying on pre-defined low-level image features, our method adaptively predicts object boundaries according to image content and user interactions.
Video Frame Interpolation via Adaptive Separable Convolution
Our method develops a deep fully convolutional neural network that takes two input frames and estimates pairs of 1D kernels for all pixels simultaneously.
Ranked #8 on
Video Frame Interpolation
on Middlebury
Spatial-Semantic Image Search by Visual Feature Synthesis
We train a convolutional neural network to synthesize appropriate visual features that captures the spatial-semantic constraints from the user canvas query.
Video Frame Interpolation via Adaptive Convolution
Video frame interpolation typically involves two steps: motion estimation and pixel synthesis.
Composition-Preserving Deep Photo Aesthetics Assessment
Deep convolutional neural network (ConvNet) methods have recently shown promising results for aesthetics assessment.
Ranked #6 on
Aesthetics Quality Assessment
on AVA
Kernel Fusion for Better Image Deblurring
This Gaussian Conditional Random Fields-based kernel fusion method not only models how individual kernels are fused at each kernel element but also the interaction of kernel fusion among multiple kernel elements.
Saliency Aggregation: A Data-Driven Approach
Our idea is to use data-driven approaches to saliency aggregation that appropriately consider the performance gaps among individual methods and the performance dependence of each method on individual images.
