A deep historical LSTM model improves tennis shot recognition from RGB videos.
problem Improving action recognition from RGB video input for sports analysis.
method Convolutional Neural Network (CNN) and Weighted Long Short-Term Memory (LSTM) for 3D tennis shot recognition.
result The method achieves better performance than state-of-the-art baselines for tennis shot recognition.
New method learns robot actions from videos without explicit labels.
problem Training robots to perform tasks from few demonstrations.
method Uses images and text for task-agnostic and general representation, synthesizes hallucinated actions, and applies dense correspondences.
result Trains robot policies solely from RGB videos, achieving diverse tasks across different robots and environments.
ESE-FN improves elderly activity recognition accuracy.
problem Recognizing individual actions and human-object interactions in elderly activities.
method Exploits multi-modal features from RGB videos and skeleton sequences using ESE attentions and a new Multi-modal Loss.
result ESE-FN achieves best accuracy on ETRI-Activity3D dataset.
This paper explores the capabilities of convolutional neural networks to deal with a task that is easily manageable for humans: perceiving 3D pose of a human body from varying angles. However, in our approach, we are restricted to using a monocular vision system. For this purpose, we apply a convolutional neural networ…
A new data-level recombination strategy improves RGB-D salient object detection.
problem RGB-D salient object detection struggles with depth information.
method Proposes a novel data-level recombination strategy to fuse RGB and depth data before feature extraction.
result Achieves a new state-of-the-art performance in RGB-D salient object detection.
Scene recognition with RGB images has been extensively studied and has reached very remarkable recognition levels, thanks to convolutional neural networks (CNN) and large scene datasets. In contrast, current RGB-D scene data is much more limited, so often leverages RGB large datasets, by transferring pretrained RGB CNN…
New architecture for RGB-D object recognition outperforms existing methods.
problem Improving object recognition in RGB-D cameras.
method RCFusion architecture combining RGB and depth information.
result RCFusion outperforms existing methods on standard datasets.
Aerial robot estimates human pose and path using dynamic classifier selection.
problem Estimating human pose and trajectory from aerial video.
method Dynamic classifier selection architecture; perspective correction; HOG and CNN features; 64 pose-viewpoint classes.
result Dynamic classifier selection improves efficiency and accuracy.
Study develops sign recognition system for DHH users.
problem Accessibility of voice-controlled devices for Deaf and Hard-of-Hearing users.
method Multimodal data (RGB video and skeletal data) for sign language recognition using deep learning.
result Validation on GMUASL51 dataset of 12 users and 13107 samples across 51 signs.
The paper explores methods to construct knots with diffeomorphic 0-traces.
problem Constructing knots with diffeomorphic 0-traces. method Survey of Gompf-Miyazaki's dualizable pattern, Abe-Jong-Omae-Takeuchi's band presentation, and RGB-diagram.
result A sufficient condition for two knots obtained by Abe-Jong-Omae-Takeuchi's method to coincide.
CURL uses neural curves to enhance global image properties.
problem Global image enhancement using neural networks.
method CURL is a multi-colour space neural retouching block trained in HSV, CIELab, and RGB color spaces.
result CURL produces state-of-the-art image quality in RGB-to-RGB and RAW-to-RGB transformations.
GWHD dataset offers 4,700 high-res images of wheat heads.
problem Challenges in wheat head detection from high-resolution imagery.
method Large, diverse dataset with detailed metadata.
result Benchmark for wheat head detection methods.
Generative models create H&E-stained and destained prostate biopsy images.
problem Lack of H&E-stained prostate biopsy images.
method Conditional GAN for H&E staining, destaining model learning from stained to non-stained images.
result Generated images maintain structural similarity to non-stained biopsy.
A new framework uses pixel-based images for realistic cloth animations.
problem Creating virtual cloth deformations that closely match real clothing.
method Reinterpreting cloth deformation as a 2D pattern space and using CNNs.
result Our approach achieves realistic cloth animations without accurate body shapes.
Project aims to improve robot vision by adapting to new environments.
problem Robots struggle to recognize objects in new settings.
method Selected and evaluated state-of-the-art DA methods on various datasets.
result Training a good object classifier remains challenging.
The introduction of cheap RGB-D cameras, stereo cameras, and LIDAR devices has given the computer vision community 3D information that conventional RGB cameras cannot provide. This data is often stored as a point cloud. In this paper, we present a novel method to apply the concept of convolutional neural networks to th…
Worldsheet wraps a 3D mesh sheet onto a single image to synthesize novel views.
problem Synthesizing novel views from a single image with large viewpoint changes.
method Shrink-wrapping a planar mesh sheet onto the input image, consistent with learned depth.
result Worldsheet consistently outperforms prior methods on single-image view synthesis.
Enhances SSL methods with depth cues for better image understanding.
problem Lack of depth cues in 2D image pixel maps limits SSL performance.
method Integrates depth signals from a pretrained monocular RGB-to-depth model into contrastive learning frameworks.
result Improves SSL methods' robustness and generalization with depth signals.
Framework fuses RGB images and depth maps for self-driving car control.
problem Fault tolerance in self-driving cars with sensor failures.
method Deep neural network architecture for sensor fusion.
result Framework can learn to use relevant sensor information even when one fails.
Deep learning continues to push state-of-the-art performance for the semantic segmentation of color (i.e., RGB) imagery; however, the lack of annotated data for many remote sensing sensors (i.e. hyperspectral imagery (HSI)) prevents researchers from taking advantage of this recent success. Since generating sensor speci…
Paper proposes a time-frequency analysis method for blind modulation classification in MIMO systems.
problem Blind modulation classification in MIMO systems with overlapping signals and unknown channel parameters.
method Time-frequency analysis using windowed short-time Fourier transform, conversion to RGB spectrogram images, convolutional neural network for classification, decision fusion.
result Proposed scheme achieves high classification accuracy at different SNRs, outperforming existing methods.
Ground-A-Video edits videos without training, preserving intended changes.
problem Complex multi-attribute video editing with omitted or wrong changes.
method Grounding-guided video-to-video translation with Cross-Frame Gated Attention.
result Zero-shot multi-attribute video editing with improved accuracy and frame consistency.
CB-GLNs learn video data's complex dependencies via graph representation.
problem Capturing complex dependency structures in sequential data like videos.
method Represent video data as a graph, find compositional dependencies via graph-cut and message passing.
result CB-GLNs efficiently learn video data's semantic compositional structure.
RaMViD uses diffusion models for video prediction and infilling.
problem Predicting and infilling missing information in videos.
method Extends image diffusion models to videos using 3D convolutions and a new conditioning technique.
result Achieves state-of-the-art results on video prediction benchmarks.
Current deep learning results on video generation are limited while there are only a few first results on video prediction and no relevant significant results on video completion. This is due to the severe ill-posedness inherent in these three problems. In this paper, we focus on human action videos, and propose a gene…
New metric for video generation models, addressing quality, coherence, and diversity.
problem Lack of metrics for evaluating generative models of video.
method Proposed Fréchet Video Distance (FVD) and StarCraft 2 Videos (SCV) benchmark.
result FVD correlates well with human judgment of generated videos.
LumièreNet creates lecture videos from audio narration.
problem Creating high-quality lecture videos from audio narration.
method Modular deep-learning architecture that learns from audio to video.
result Synthesizes high-quality lecture videos from any length of audio.
Paper defends against adversarial videos by detecting and reducing imperceptible perturbations.
problem Adversarial videos can fool well-trained video classification models.
method Temporal consistency between frames and spatial denoising to detect and reduce perturbations.
result The proposed method significantly improves robustness against adversarial attacks.
Paper improves video categorization using temporal coherence.
problem Video categorization in multiple modalities.
method Temporal coherence-based regularization for multimodal models.
result Models with temporal coherence outperform state-of-the-art.
Improves video search by balancing text and visual modalities.
problem Modality imbalance in video search models, focusing mainly on text matching.
method Proposes MBVR with MS samples and DM to balance modalities.
result Empirically shows significant improvement in modality balance and search effectiveness.
SLAM-net learns to navigate visually in challenging indoor environments.
problem Challenges in SLAM for visual robot navigation, especially in noisy conditions.
method Differentiable SLAM Network (SLAM-net) that encodes a particle filter SLAM algorithm in a differentiable graph and learns components through backpropagation.
result Significantly outperforms ORB-SLAM in noisy conditions and improves the Habitat Challenge 2020 PointNav task.
A new video prediction model treats videos as continuous processes, reducing sampling steps and improving efficiency.
problem Efficiency and temporal coherence in video prediction models.
method Treats videos as a continuous multi-dimensional process, reducing sampling steps.
result Reduction of 75% sampling steps, state-of-the-art performance on benchmark datasets.
UDVD uses deep learning to denoise videos without supervision.
problem Lack of clean video data for training deep learning models.
method UDVD is a CNN trained solely on noisy video data, adapting to local motion.
result UDVD performs as well as supervised methods, even with limited training data.
ES-VAE models skeletal pose trajectories by removing nuisance factors.
problem Handling camera orientation, subject scale, viewpoint, and execution speed in skeletal data.
method ES-VAE uses TSRVF representation on Kendall's shape manifold to isolate shape dynamics.
result ES-VAE outperforms standard VAEs and sequence modeling baselines in gait cycle prediction and action recognition.
Generative model for high-resolution video generation.
problem Challenges in generating high-resolution videos due to memory and training stability limitations.
method Progressive growing of sliced Wasserstein GANs (SWGAN) for incremental spatiotemporal information learning.
result Generated photorealistic face videos of 256x256x32 resolution with an inception score of 14.57.
Proposes TDNs for learning complex video structures.
problem Complex temporal dependencies in sequential data, especially videos.
method Temporal Dependency Networks (TDNs) using graph representations and graph convolutions.
result Efficiently learns complex semantic structures of video data.
SummaryNet automates video summarisation using deep learning.
problem Creating informative video summaries from videos.
method Two-stream convolutional network for spatial and temporal features, encoder-decoder model for salient features, sigmoid regression with LSTM for frame probability.
result SummaryNet achieves comparable or better results than state-of-the-art methods on benchmark datasets.
Paper proposes SMFN for high-res spherical video super-resolution.
problem Super-resolution of 360-degree panoramic videos is expensive and challenging.
method Deformable convolutions, mixed attention mechanism, dual learning strategy, weighted mean square error loss function.
result The proposed SMFN method improves super-resolution of equatorial regions in 360-degree videos.
Generative model produces high-fidelity video samples.
problem Generating high-fidelity videos from complex datasets.
method Large GAN trained on Kinetics-600 dataset, using a computationally efficient discriminator.
result Achieved state-of-the-art metrics in video synthesis and prediction.
Generative model learns compact codes for video recovery.
problem Efficiently represent and reconstruct videos from missing data.
method Generative network trained to map compact latent codes to images, with low-rank and similarity constraints.
result Can recover true video sequences even if not in pretrained network's range.
Paper investigates trade-off between video bitrate and CNN accuracy.
problem Network bandwidth and energy consumption issues in video classification.
method Only retain motion vector and select texture information at reduced bitrates.
result Achieved 11%-94% saving in bitrate with marginal accuracy loss.
Paper proposes new principles and framework for AVC learning from user-generated videos.
problem Challenges in learning audio-visual correspondence from short-term user-generated videos.
method Introduced new principles and a framework to facilitate AVC learning from videos' themes.
result Proposed approach outperformed baseline by 23.15% on KWAI-AD-AudVis corpus.
Lower-dimensional video discriminators improve GAN performance.
problem High curvature in unconstrained video discriminator loss surfaces.
method Proposed Lower-Dimensional Video Discriminators (LDVD GANs).
result LDVD GANs double Temporal-GAN performance and achieve state-of-the-art performance.
Study presents a low-cost local motion planner for vineyard navigation.
problem Autonomous navigation in vineyards with limited resources.
method RGB-D camera, dual layer control algorithm, deep learning synergy.
result Robust motion planning for vineyard navigation achieved.
System automates discovery and classification of training videos for career progression.
problem Difficulties in planning and navigating career paths due to changing job requirements and emerging sectors.
method Extracted educational videos, built a machine learning classifier, and optimized probability thresholds.
result Significant improvements in model performance by incorporating video attributes.
With the growth of user-generated content, we observe the constant rise of the number of companies, such as search engines, content aggregators, etc., that operate with tremendous amounts of web content not being the services hosting it. Thus, aiming to locate the most important content and promote it to the users, the…
Scalable system predicts hot videos for peak VOD service.
problem Improving peak service quality of video on demand.
method Two neural networks: clustering and dispatch policy. Clustering reduces video numbers, dispatch policy ranks videos with probabilities. Networks are trained end-to-end.
result Average prediction accuracy of 17% compared to 3% baseline, for same number of dispatches.
This paper improves video summarization using a new algorithm and dataset.
problem Efficiently summarizing videos for browsing and searching.
method Improves sequential determinantal point process (SeqDPP) with a large-margin algorithm and a new probabilistic distribution.
result Significantly improved video summarization model with better user input integration and diversity.