Unpaired video-to-video translation aims to translate videos between a source and a target domain without the need of paired training data, making it more feasible for real applications. Unfortunately, the translated videos generally suffer from temporal and semantic inconsistency. To address this, many existing works adopt spatiotemporal consistency constraints incorporating temporal information based on motion estimation. However, the inaccuracies in the estimation of motion deteriorate the quality of the guidance towards spatiotemporal consistency, which leads to unstable translation. In this work, we propose a novel paradigm that regularizes the spatiotemporal consistency by synthesizing motions in input videos with the generated optical flow instead of estimating them. Therefore, the synthetic motion can be applied in the regularization paradigm to keep motions consistent across domains without the risk of errors in motion estimation. Thereafter, we utilize our unsupervised recycle and unsupervised spatial loss, guided by the pseudo-supervision provided by the synthetic optical flow, to accurately enforce spatiotemporal consistency in both domains. Experiments show that our method is versatile in various scenarios and achieves state-of-the-art performance in generating temporally and semantically consistent videos. Code is available at: https://github.com/wangkaihong/Unsup_Recycle_GAN/.
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Daimler TSS（戴姆勒TSS公司）；Facebook AI Research（脸书人工智能研究实验室）；MIT（麻省理工学院）；Harvard Medical School（哈佛医学院）；KU Leuven（鲁汶大学）；ETH Zurich（苏黎世联邦理工学院）
Action segmentation refers to inferring boundaries of semantically consistent visual concepts in videos and is an important requirement for many video understanding tasks. For this and other video understanding tasks, supervised approaches have achieved encouraging performance but require a high volume of detailed frame-level annotations. We present a fully automatic and unsupervised approach for segmenting actions in a video that does not require any training. Our proposal is an effective temporally-weighted hierarchical clustering algorithm that can group semantically consistent frames of th…
Many applications of unpaired image-to-image translation require the input contents to be preserved semantically during translations. Unaware of the inherently unmatched semantics distributions between source and target domains, existing distribution matching methods (i.e., GAN-based) can give undesired solutions. In particular, although producing visually reasonable outputs, the learned models usually flip the semantics of the inputs. To tackle this without using extra supervision, we propose to enforce the translated outputs to be semantically invariant w.r.t. small perceptual variations of …
We present ConCur, a contrastive video representation learning method that uses curriculum learning to impose a dynamic sampling strategy in contrastive training. More specifically, ConCur starts the contrastive training with easy positive samples (temporally close and semantically similar clips), and as the training progresses, it increases the temporal span effectively sampling hard positives (temporally away and semantically dissimilar). To learn better context-aware representations, we also propose an auxiliary task of predicting the temporal distance between a positive pair of clips. We c…
NCT/UCC Dresden（德累斯顿国家肿瘤疾病中心/大学癌症中心）；CeTI, TU Dresden（德累斯顿工业大学触觉互联网卓越中心）；University Hospital Dresden（德累斯顿大学医院）
Research in unpaired video translation has mainly focused on short-term temporal consistency by conditioning on neighboring frames. However for transfer from simulated to photorealistic sequences, available information on the underlying geometry offers potential for achieving global consistency across views. We propose a novel approach which combines unpaired image translation with neural rendering to transfer simulated to photorealistic surgical abdominal scenes. By introducing global learnable textures and a lighting-invariant view-consistency loss, our method produces consistent translation…
SurgViVQA: Temporally-Grounded Video Question Answering for Surgical Scene Understanding
Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB)（电子、信息与生物工程系）；Politecnico di Milano（米兰理工大学）；IRCCS Humanitas Research Hospital（IRCCS人类itas研究医院）；UCL Hawkes Institute and Department of Computer Science（UCL Hawkes研究所和计算机科学系）；University College London（伦敦大学学院）；University of Manchester（曼彻斯特大学）
We propose a method for the unsupervised reconstruction of a temporally-coherent sequence of surfaces from a sequence of time-evolving point clouds, yielding dense, semantically meaningful correspondences between all keyframes. We represent the reconstructed surface as an atlas, using a neural network. Using canonical correspondences defined via the atlas, we encourage the reconstruction to be as isometric as possible across frames, leading to semantically-meaningful reconstruction. Through experiments and comparisons, we empirically show that our method achieves results that exceed that state…
We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. It yields dense and semantically meaningful correspondences between frames. We represent the reconstructed surfaces as atlases computed by a neural network, which enables us to establish correspondences between frames. The key to making these correspondences semantically meaningful is to guarantee that the metric tensors computed at corresponding points are as similar as possible. We have devised an optimization strategy that makes our method robust…
Tsinghua-Berkeley Shenzhen Institute（清华-伯克利深圳学院）；Tsinghua University（清华大学）；Tencent AI Lab（腾讯人工智能实验室）
Temporal sentence grounding in videos aims to detect and localize one target video segment, which semantically corresponds to a given sentence. Existing methods mainly tackle this task via matching and aligning semantics between a sentence and candidate video segments, while neglect the fact that the sentence information plays an important role in temporally correlating and composing the described contents in videos. In this paper, we propose a novel semantic conditioned dynamic modulation (SCDM) mechanism, which relies on the sentence semantics to modulate the temporal convolution operations …
Courant Institute, NYU（纽约大学柯朗研究所）；University of California, Berkeley（加州大学伯克利分校）；Google Inc.（谷歌公司）；Facebook AI Research（脸书人工智能研究院）
Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled video data, using the assumption that adjacent video frames contain semantically similar information. This assumption is exploited to train a convolutional pooling auto-encoder regularized by slowness and sparsity. We establish a connection between slow feature learning to metric learning and show that the trained encoder can be used to define a more tempora…
AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration
Kling Team, Kuaishou Technology（快手科技 Kling 团队）；New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所模式识别新实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Peking University（北京大学）；Nanjing University（南京大学）
DATE: Dynamic Absolute Time Enhancement for Long Video Understanding
Beihang University（北京航空航天大学）；Dcar, ByteDance（字节跳动Dcar部门）；Qfin Holdings,Inc（Qfin控股公司）；MAIS, Institute of Automation, Chinese Academy of Sciences（自动化研究所，中国科学院）
Our work explores temporal self-supervision for GAN-based video generation tasks. While adversarial training successfully yields generative models for a variety of areas, temporal relationships in the generated data are much less explored. Natural temporal changes are crucial for sequential generation tasks, e.g. video super-resolution and unpaired video translation. For the former, state-of-the-art methods often favor simpler norm losses such as $L^2$ over adversarial training. However, their averaging nature easily leads to temporally smooth results with an undesirable lack of spatial detail…
Mitsubishi Electric Research Labs (MERL)（三菱电机研究实验室（MERL））
Unpaired image-to-image translation is the problem of mapping an image in the source domain to one in the target domain, without requiring corresponding image pairs. To ensure the translated images are realistically plausible, recent works, such as Cycle-GAN, demands this mapping to be invertible. While, this requirement demonstrates promising results when the domains are unimodal, its performance is unpredictable in a multi-modal scenario such as in an image segmentation task. This is because, invertibility does not necessarily enforce semantic correctness. To this end, we present a semantica…
The University of Hong Kong（香港大学）；Tencent AI Lab（腾讯人工智能实验室）
In this paper, we address a novel task, namely weakly-supervised spatio-temporally grounding natural sentence in video. Specifically, given a natural sentence and a video, we localize a spatio-temporal tube in the video that semantically corresponds to the given sentence, with no reliance on any spatio-temporal annotations during training. First, a set of spatio-temporal tubes, referred to as instances, are extracted from the video. We then encode these instances and the sentence using our proposed attentive interactor which can exploit their fine-grained relationships to characterize their ma…
Facebook AI Research（脸书人工智能研究院）；Courant Institute of Mathematical Science（库朗数学科学研究所）
Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled video data, using the assumption that adjacent video frames contain semantically similar information. This assumption is exploited to train a convolutional pooling auto-encoder regularized by slowness and sparsity. We establish a connection between slow feature learning to metric learning and show that the trained encoder can be used to define a more tempora…
MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering
School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Digital China Group（数字中国集团）
Amazon Lab126（亚马逊Lab126）；School of Computing, University of Utah（犹他大学计算学院）
Recovering 3D human pose from 2D joints is a highly unconstrained problem. We propose a novel neural network framework, PoseNet3D, that takes 2D joints as input and outputs 3D skeletons and SMPL body model parameters. By casting our learning approach in a student-teacher framework, we avoid using any 3D data such as paired/unpaired 3D data, motion capture sequences, depth images or multi-view images during training. We first train a teacher network that outputs 3D skeletons, using only 2D poses for training. The teacher network distills its knowledge to a student network that predicts 3D pose …
Video inpainting aims to fill spatio-temporal holes with plausible content in a video. Despite tremendous progress of deep neural networks for image inpainting, it is challenging to extend these methods to the video domain due to the additional time dimension. In this work, we propose a novel deep network architecture for fast video inpainting. Built upon an image-based encoder-decoder model, our framework is designed to collect and refine information from neighbor frames and synthesize still-unknown regions. At the same time, the output is enforced to be temporally consistent by a recurrent f…
Beijing Film Academy（北京电影学院）；Tel-Aviv University（特拉维夫大学）；Peking University（北京大学）；The Hebrew University of Jerusalem（耶路撒冷希伯来大学）
Transferring the motion style from one animation clip to another, while preserving the motion content of the latter, has been a long-standing problem in character animation. Most existing data-driven approaches are supervised and rely on paired data, where motions with the same content are performed in different styles. In addition, these approaches are limited to transfer of styles that were seen during training. In this paper, we present a novel data-driven framework for motion style transfer, which learns from an unpaired collection of motions with style labels, and enables transferring mot…
Iskenderun Technical University（伊斯肯德伦技术大学）；Imperial College London（帝国理工学院）；Hacettepe University（哈塞特佩大学）；Koc University（科奇大学）
Giving machines the ability to imagine possible new objects or scenes from linguistic descriptions and produce their realistic renderings is arguably one of the most challenging problems in computer vision. Recent advances in deep generative models have led to new approaches that give promising results towards this goal. In this paper, we introduce a new method called DiCoMoGAN for manipulating videos with natural language, aiming to perform local and semantic edits on a video clip to alter the appearances of an object of interest. Our GAN architecture allows for better utilization of multiple…
In this paper, we tackle the problem of human motion transfer, where we synthesize novel motion video for a target person that imitates the movement from a reference video. It is a video-to-video translation task in which the estimated poses are used to bridge two domains. Despite substantial progress on the topic, there exist several problems with the previous methods. First, there is a domain gap between training and testing pose sequences--the model is tested on poses it has not seen during training, such as difficult dancing moves. Furthermore, pose detection errors are inevitable, making …
Unpaired image translation algorithms can be used for sim2real tasks, but many fail to generate temporally consistent results. We present a new approach that combines differentiable rendering with image translation to achieve temporal consistency over indefinite timescales, using surface consistency losses and \emph{neural neural textures}. We call this algorithm TRITON (Texture Recovering Image Translation Network): an unsupervised, end-to-end, stateless sim2real algorithm that leverages the underlying 3D geometry of input scenes by generating realistic-looking learnable neural textures. By s…
Saarland Informatics Campus（萨尔兰信息学园区）；German Research Centre for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；Max Planck Institute for Informatics (MPII)（马克斯·普朗克信息学研究所（MPII））
MotionAdapter: Video Motion Transfer via Content-Aware Attention Customization
Hangzhou Dianzi University（杭州电子科技大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；The Hong Kong University of Science and Technology（香港科技大学）；Ocean University of China（中国海洋大学）；Singapore Management University（新加坡管理大学）
