This paper proposes a method to gain extra supervision via multi-task learning for multi-modal video question answering. Multi-modal video question answering is an important task that aims at the joint understanding of vision and language. However, establishing large scale dataset for multi-modal video question answeri…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “video tasks”
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.
Introduces Motion Programs for better video analysis of human motion.
problem Current video analysis focuses on raw pixels or keypoints, missing higher-level motion primitives.
method Introduces Motion Programs as a neuro-symbolic representation of motions as a composition of high-level primitives.
result Motion Programs accurately describe diverse human motions and improve downstream tasks.
VLEngagement: A Dataset of Scientific Video Lectures for Evaluating Population-based Engagementcs.CY
A dataset for evaluating engagement with scientific video lectures.
problem Challenges in managing learning resources due to rapid creation of video lectures.
method Introduction of VLEngagement dataset with content-based and video-specific features, and metrics related to user engagement.
result The largest and most diverse publicly available dataset for understanding context-agnostic engagement in video lectures.
The popularity of Deep Learning for real-world applications is ever-growing. With the introduction of high performance hardware, applications are no longer limited to image recognition. With the introduction of more complex problems comes more and more complex solutions, and the increasing need for explainable AI. Deep…
Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition. For the task of capturing temporal structure in video, however, there still remain numerous open research questions. Current research suggests using a simple temporal feature pooling…
One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Videocs.LG
Due to burdensome data requirements, learning from demonstration often falls short of its promise to allow users to quickly and naturally program robots. Demonstrations are inherently ambiguous and incomplete, making correct generalization to unseen situations difficult without a large number of demonstrations in varyi…
Over the past one hundred years, the classic teaching methodology of "see one, do one, teach one" has governed the surgical education systems worldwide. With the advent of Operation Room 2.0, recording video, kinematic and many other types of data during the surgery became an easy task, thus allowing artificial intelli…
Transformer is a popularly used neural network architecture, especially for language understanding. We introduce an extended and unified architecture that can be used for tasks involving a variety of modalities like image, text, videos, etc. We propose a spatio-temporal cache mechanism that enables learning spatial dim…
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.
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.
Video summarisation can be posed as the task of extracting important parts of a video in order to create an informative summary of what occurred in the video. In this paper we introduce SummaryNet as a supervised learning framework for automated video summarisation. SummaryNet employs a two-stream convolutional network…
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.
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.
Generative models of natural images have progressed towards high fidelity samples by the strong leveraging of scale. We attempt to carry this success to the field of video modeling by showing that large Generative Adversarial Networks trained on the complex Kinetics-600 dataset are able to produce video samples of subs…
Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider instructional videos where there are tens of millions of them on the Internet. We propose a…
Emotional content is a crucial ingredient in user-generated videos. However, the sparsity of emotional expressions in the videos poses an obstacle to visual emotion analysis. In this paper, we propose a new neural approach, Bi-stream Emotion Attribution-Classification Network (BEAC-Net), to solve three related emotion …
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However, most of sequential data, as seen with videos, have complex dependency structures that imply variable-length semantic flows and their composi…
MTLE: A Multitask Learning Encoder of Visual Feature Representations for Video and Movie Descriptioncs.LG
Learning visual feature representations for video analysis is a daunting task that requires a large amount of training samples and a proper generalization framework. Many of the current state of the art methods for video captioning and movie description rely on simple encoding mechanisms through recurrent neural networ…
Recent advances in deep generative models have lead to remarkable progress in synthesizing high quality images. Following their successful application in image processing and representation learning, an important next step is to consider videos. Learning generative models of video is a much harder task, requiring a mod…
We consider the problem of learning multi-stage vision-based tasks on a real robot from a single video of a human performing the task, while leveraging demonstration data of subtasks with other objects. This problem presents a number of major challenges. Video demonstrations without teleoperation are easy for humans to…
TokenCut detects and segments objects in images and videos without supervision.
problem Detecting and segmenting salient objects in images and videos without labeled data.
method Graph-based approach using self-supervised transformer features and Normalized Cut algorithm.
result Achieves state-of-the-art results on various detection and segmentation tasks.
We present a new model DrNET that learns disentangled image representations from video. Our approach leverages the temporal coherence of video and a novel adversarial loss to learn a representation that factorizes each frame into a stationary part and a temporally varying component. The disentangled representation can …
In the few-shot scenario, a learner must effectively generalize to unseen classes given a small support set of labeled examples. While a relatively large amount of research has gone into few-shot learning for image classification, little work has been done on few-shot video classification. In this work, we address the …
We design a dispatch system to improve the peak service quality of video on demand (VOD). Our system predicts the hot videos during the peak hours of the next day based on the historical requests, and dispatches to the content delivery networks (CDNs) at the previous off-peak time. In order to scale to billions of vide…
The extension of image generation to video generation turns out to be a very difficult task, since the temporal dimension of videos introduces an extra challenge during the generation process. Besides, due to the limitation of memory and training stability, the generation becomes increasingly challenging with the incre…
In this paper we consider the problem of video-based person re-identification, which is the task of associating videos of the same person captured by different and non-overlapping cameras. We propose a Siamese framework in which video frames of the person to re-identify and of the candidate one are processed by two ide…
Generates coherent 3D scenes from monocular videos without supervision.
problem Lack of 3D scene modeling in video generation models.
method Trains a model to generate 3D scenes with moving objects and a background from monocular videos.
result Trained model generates coherent 3D scenes with multiple moving objects and a background.
Video classification is a challenging task in computer vision. Although Deep Neural Networks (DNNs) have achieved excellent performance in video classification, recent research shows adding imperceptible perturbations to clean videos can make the well-trained models output wrong labels with high confidence. In this pap…
We study a generalized setup for learning from demonstration to build an agent that can manipulate novel objects in unseen scenarios by looking at only a single video of human demonstration from a third-person perspective. To accomplish this goal, our agent should not only learn to understand the intent of the demonstr…
Making predictions of future frames is a critical challenge in autonomous driving research. Most of the existing methods for video prediction attempt to generate future frames in simple and fixed scenes. In this paper, we propose a novel and effective optical flow conditioned method for the task of video prediction wit…
AMS improves video inference on edge devices by adapting a small model with online knowledge distillation.
problem High computation cost of Deep Neural Networks for real-time video inference on edge devices.
method AMS uses a remote server to continually train and adapt a small model on edge devices, using online knowledge distillation from a large model.
result 0.4--17.8 percent mean Intersection-over-Union improvement in video semantic segmentation.
Our goal is to predict future video frames given a sequence of input frames. Despite large amounts of video data, this remains a challenging task because of the high-dimensionality of video frames. We address this challenge by proposing the Decompositional Disentangled Predictive Auto-Encoder (DDPAE), a framework that …
Unified model trained on images and videos using masked autoencoding.
problem Training a single model for multiple visual modalities.
method Masked autoencoding on a Vision Transformer.
result Unified model achieves comparable or better performance than single-modality models.
In this paper, we present a method for learning from video demonstrations by using human feedback to construct a mapping between the standard representation of the agent and the visual representation of the demonstration. In this way, we leverage the advantages of both these representations, i.e., we learn the policy u…
LVTINO improves high-definition video restoration with consistent temporal details.
problem Restoring high-definition video with fine spatial detail and temporal consistency.
method LVTINO uses Video Consistency Models to bypass frame-by-frame image-based LDMs, achieving perceptual quality and computational efficiency.
result Significant perceptual improvements over current methods, achieving state-of-the-art quality with minimal evaluations.
New deep-unfolded network improves video background separation.
problem Video foreground-background separation.
method Deep unfolding of an iterative RPCA algorithm with adaptive learning.
result Proposed network outperforms state-of-the-art in video foreground-background separation.
In this paper, we deal with two challenges for measuring the similarity of the subject identities in practical video-based face recognition - the variation of the head pose in uncontrolled environments and the computational expense of processing videos. Since the frame-wise feature mean is unable to characterize the po…
Rolling Diffusion improves video prediction by progressively corrupting frames based on their temporal position.
problem Improving video prediction accuracy by accounting for temporal dynamics.
method A sliding window denoising process that assigns more noise to frames that appear later in a sequence.
result Rolling Diffusion outperforms standard diffusion models in tasks with complex temporal dynamics.
This paper proposes a self-supervised learning approach for video features that results in significantly improved performance on downstream tasks (such as video classification, captioning and segmentation) compared to existing methods. Our method extends the BERT model for text sequences to the case of sequences of rea…
Lipreading has a lot of potential applications such as in the domain of surveillance and video conferencing. Despite this, most of the work in building lipreading systems has been limited to classifying silent videos into classes representing text phrases. However, there are multiple problems associated with making lip…
New RL method learns from passive data by modeling intentions.
problem Learning from passive data like videos without rewards or actions.
method Model intentions using temporal difference learning, learning representations from raw data.
result Successfully learns features from passive data that accelerate downstream RL tasks.
This paper addresses the challenging task of video captioning which aims to generate descriptions for video data. Recently, the attention-based encoder-decoder structures have been widely used in video captioning. In existing literature, the attention weights are often built from the information of an individual modali…
Recent progress in using recurrent neural networks (RNNs) for image description has motivated the exploration of their application for video description. However, while images are static, working with videos requires modeling their dynamic temporal structure and then properly integrating that information into a natural…
Paper proposes a new LSTM model for spatio-temporal learning.
problem Challenging video tasks require learning long-term spatio-temporal correlations.
method Introduces a higher-order convolutional LSTM model with tensor train decomposition.
result Model achieves state-of-the-art performance with significantly fewer parameters.
Seq2Tens uses tensors to efficiently represent sequences, improving performance on time series and video tasks.
problem Challenges in analyzing sequential data due to complex dependencies and non-commutativity.
method Uses tensor algebra to capture dependencies and low-rank tensor projections to manage computational complexity.
result State-of-the-art performance on multivariate time series classification and video generation benchmarks.
In this paper, we examined the zero-shot activity recognition task with the usage of videos. We introduce an auto-encoder based model to construct a multimodal joint embedding space between the visual and textual manifolds. On the visual side, we used activity videos and a state-of-the-art 3D convolutional action recog…
Spatial audio is an essential medium to audiences for 3D visual and auditory experience. However, the recording devices and techniques are expensive or inaccessible to the general public. In this work, we propose a self-supervised audio spatialization network that can generate spatial audio given the corresponding vide…