United States

We study unsupervised video representation learning that seeks to learn both motion and appearance features from unlabeled video only, which can be reused for downstream tasks such as action recognition. This task, however, is extremely challenging due to 1) the highly complex spatial-temporal information in videos and 2) the lack of labeled data for training. Unlike representation learning for static images, it is difficult to construct a suitable self-supervised task to effectively model both motion and appearance features. More recently, several attempts have been made to learn video representation through video playback speed prediction. However, it is non-trivial to obtain precise speed labels for the videos. More critically, the learned models may tend to focus on motion patterns and thus may not learn appearance features well. In this paper, we observe that the relative playback speed is more consistent with motion patterns and thus provides more effective and stable supervision for representation learning. Therefore, we propose a new way to perceive the playback speed and exploit the relative speed between two video clips as labels. In this way, we are able to effectively perceive speed and learn better motion features. Moreover, to ensure the learning of appearance features, we further propose an appearance-focused task, where we enforce the model to perceive the appearance difference between two video clips. We show that jointly optimizing the two tasks consistently improves the performance on two downstream tasks (namely, action recognition and video retrieval) w.r.t the increasing pre-training epochs. Remarkably, for action recognition on the UCF101 dataset, we achieve 93.7% accuracy without the use of labeled data for pre-training, which outperforms the ImageNet supervised pre-trained model. Our code, pre-trained models, and supplementary materials can be found at https://github.com/PeihaoChen/RSPNet.

AAAI 2021

RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

technical paper

Predicting actions from partially observed videos is challenging as the partial videos containing incomplete action executions have insufficient discriminative information for classification. Recent progress has been made through enriching the features of the observed video part or generating the features for the unobserved video part, but without explicitly modeling the fine-grained evolution of visual object relations over both space and time. In this paper, we investigate how the interaction and correlation between visual objects evolve and propose a graph growing method to anticipate future object relations from limited video observations for reliable action prediction. There are two tasks in our method. First, we work with spatial-temporal graph neural networks to reason object relations in the observed video part. Then, we synthesize the spatial-temporal relation representation for the unobserved video part via graph node generation and aggregation. These two tasks are jointly learned to enable the anticipated future relation representation informative to action prediction. Experimental results on two action video datasets demonstrate the effectiveness of our method.

Anticipating Future Relations via Graph Growing for Action Prediction

This  paper  presents  TaLNet,  a  model  for  voice  reconstruction with ultrasound tongue and optical lip videos as inputs. TaLNet  is  based  on  an  encoder-decoder  architecture.  Separate  encoders  are  dedicated  to  processing  the  tongue  and lip data streams respectively. The decoder predicts acoustic features conditioned on encoder outputs and speaker codes.To mitigate for having only relatively small amounts of dual articulatory-acoustic data available for training, and since our task here shares with text-to-speech (TTS) the common goal of  speech  generation,  we  propose  a  novel  transfer  learning strategy to exploit the much larger amounts of acoustic-only data  available  to  train  TTS  models.  For  this,  a  Tacotron  2 TTS model is first trained, and then the parameters of its decoder are transferred to the TaLNet decoder. We have evaluated our approach on an unconstrained multi-speaker voice recovery task. Our results show the effectiveness of both the proposed  model  and  the  transfer  learning  strategy.  Speech reconstructed  using  our  proposed  method  significantly  outperformed all baselines (DNN, BLSTM and without transfer learning) in terms of both naturalness and intelligibility. When using an ASR model decoding the recovery speech, the WER of our proposed method is relatively reduced over 30% compared to baselines.

TaLNet: Voice Reconstruction from Tongue and Lip Articulation with Transfer Learning from Text-to-Speech Synthesis

In this paper, we propose a novel method, referred to as incomplete multi-view tensor spectral clustering with missing-view inferring (IMVTSC-MVI) to address the challenging multi-view clustering problem with missing views. Different from the existing methods which commonly focus on exploring the certain information of the available views while ignoring both of the hidden information of the missing views and the intra-view information of data, IMVTSC-MVI seeks to recover the missing views and explore the full information of such recovered views and available views for data clustering. In particular, IMVTSC-MVI incorporates the feature space based missing-view inferring and manifold space based similarity graph learning into a unified framework. In such a way, IMVTSC-MVI allows these two learning tasks to facilitate each other and can well explore the hidden information of the missing views. Moreover, IMVTSC-MVI introduces the low-rank tensor constraint to capture the high-order correlations of multiple views. Experimental results on several datasets demonstrate the effectiveness of IMVTSC-MVI for incomplete multi-view clustering.

Unified Tensor Framework for Incomplete Multi-View Clustering and Missing-View Inferring

Image-to-video adaptation leverages off-the-shelf learned models in labeled images to help classification in unlabeled videos, thus alleviating the high computation overhead of training a video classifier from scratch. This task is very challenging since there exist two types of domain shifts between images and videos: 1) spatial domain shift caused by static appearance variance between images and video frames, and 2) temporal domain shift caused by the absence of dynamic motion in images. Moreover, for different video classes, these two domain shifts have different effects on the domain gap and should not be treated equally during adaptation. In this paper, we propose a spatial-temporal causal inference framework for image-to-video adaptation. We first construct a spatial-temporal causal graph to infer the effects of the spatial and temporal domain shifts by performing counterfactual causality. We then learn causality-guided bidirectional heterogeneous mappings between images and videos to adaptively reduce the two domain shifts. Moreover, to relax the assumption that the label spaces of the image and video domains are the same by the existing methods, we incorporate class-wise alignment into the learning of image-video mappings to perform partial image-to-video adaptation where the image label space subsumes the video label space. Extensive experiments on several video datasets have validated the effectiveness of our proposed method.

Spatial-Temporal Causal Inference for Partial Image-to-Video Adaptation

Image-text matching plays a critical role in bridging the vision and language, and great progress has been made by exploiting the global alignment between image and sentence, or local alignments between regions and words. However, how to make the most of these alignments to infer more accurate matching scores is still underexplored. In this paper, we propose a novel Similarity Graph Reasoning and Attention Filtration (SGRAF) network for image-text matching. Specifically, the vector-based similarity representations are firstly learned to characterize the local and global alignments in a more comprehensive manner, and then the Similarity Graph Reasoning (SGR) module relying on one graph convolutional neural network is introduced to infer relation-aware similarities with both the local and global alignments. The Similarity Attention Filtration (SAF) module is further developed to integrate these alignments effectively by selectively attending on the significant and representative alignments and meanwhile casting aside the interferences of non-meaningful alignments. We demonstrate the superiority of the proposed method with achieving state-of-the-art performances on the Flickr30K and MSCOCO datasets, and the good interpretability of SGR and SAF with extensive qualitative experiments and analyses.

Similarity Reasoning and Filtration for Image-Text Matching

Generating human action proposals in untrimmed videos is an important yet challenging task with wide applications. Current methods often suffer from the noisy boundary locations and the inferior quality of confidence scores used for proposal retrieving. In this paper, we present BSN++, a new framework which exploits complementary boundary regressor and relation modeling for temporal proposal generation. First, we propose a novel boundary regressor based on the complementary characteristics of both starting and ending boundary classifiers. Specifically, we utilize the U-shaped architecture with nested skip connections to capture rich contexts and introduce bi-directional boundary matching mechanism to improve boundary precision. Second, to account for the proposal-proposal relations ignored in previous methods, we devise a proposal relation block to which includes two self-attention modules from the aspects of position and channel. Furthermore, we find that there inevitably exists data imbalanced problems in the positive/negative proposals and temporal durations, which harm the model performance on tail distributions. To relieve this issue, we introduce the scale-balanced re-sampling strategy. Extensive experiments are conducted on two popular benchmarks: ActivityNet-1.3 and THUMOS14, which demonstrate that BSN++ achieves the state-of-the-art performance. Not surprisingly, the proposed BSN++ ranked 1st place in the CVPR19 - ActivityNet challenge leaderboard on temporal action localization task.

BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation

Semantic parsing has long been a fundamental problem in natural language processing. Recently, cross-domain context-dependent semantic parsing has become a new focus of research. Central to the problem is the challenge of leveraging contextual information of both natural language queries and database schemas in the interaction history.  In this paper, we present a dynamic graph framework that is capable of effectively modelling contextual utterances, tokens, database schemas, and their complicated interaction as the conversation proceeds. The framework employs a dynamic memory decay mechanism that incorporates inductive bias to integrate enriched contextual relation representation, which is further enhanced with a powerful reranking model. At the time of writing, we demonstrate that the proposed framework outperforms all existing models by large margins, achieving new state-of-the-art performance on two large-scale benchmarks, the SParC and CoSQL datasets. Specifically, the model attains a 55.8% question-match and 30.8% interaction-match accuracy on SParC, and a 46.8% question-match and 17.0% interaction-match accuracy on CoSQL.

Dynamic Hybrid Relation Exploration Network for Cross-Domain Context-Dependent Semantic Parsing

Unsupervised hashing is important for indexing huge image or video collections without having expensive annotations available. Hashing aims to learn short binary codes for compact storage and efficient semantic retrieval. We propose an unsupervised deep hashing layer called Bi-Half Net that maximizes entropy of the binary codes. Entropy is maximal when both possible values of the bit are uniformly (half-half) distributed. To maximize bit entropy, we do not add a term to the loss function as this is difficult to optimize and tune. Instead, we design a new parameter-free network layer to explicitly force continuous image features to approximate the optimal half-half bit distribution. This layer is shown to minimize a penalized term of the Wasserstein distance between the learned continuous image features and the optimal half-half bit distribution. Experimental results on the image datasets FLICKR25K, NUS-WIDE, CIFAR-10, MS COCO, MNIST and the video datasets UCF-101 and HMDB-51 show that our approach leads to compact codes and compares favorably to the current state-of-the-art.

Deep Unsupervised Image Hashing by Maximizing Bit Entropy

Pre-training location embeddings from spatial-temporal trajectories is a fundamental procedure and very beneficial for user next location prediction. In the real world, a location usually has variable functionalities under different contextual environments. If the exact functions of a location in the trajectory can be reflected in its embedding, the accuracy of user next location prediction should be improved. Yet, existing location embeddings pre-trained on trajectories are mostly based on distributed word representations, which mix a location's various functionalities into one latent representation vector. To address this problem, we propose a Context and Time aware Location Embedding (CTLE) model, which calculates a location's representation vector with consideration of its specific contextual neighbors in trajectories. In this way, the multi-functional properties of locations can be properly tackled. Furthermore, in order to incorporate temporal information in trajectories into location embeddings, we propose a subtle temporal encoding module and a novel pre-training objective, which further improve the quality of location embeddings. We evaluate our proposed model on two real-world mobile user trajectory datasets. The experimental results demonstrate that, compared with the existing embedding methods, our CTLE model can pre-train higher quality location embeddings and significantly improve the performance of downstream user location prediction models.

Pre-Training Context and Time Aware Location Embeddings from Spatial-Temporal Trajectories for User Next Location Prediction

Weakly-Supervised Object Detection (WSOD) aims at training a model with limited and coarse annotations for precisely locating the regions of objects. Existing works solve the WSOD problem by using a two-stage framework, i.e., generating candidate bounding boxes with weak supervision information and then refining them by directly employing supervised object detection models. However, most of such works mainly focus on the performance boosting of the first stage, while ignoring the better usage of generated candidate bounding boxes. To address this issue, we propose a new two-stage framework for WSOD, named GradingNet, which can make good use of the generated candidate bounding boxes. Specifically, the proposed GradingNet consists of two modules: Boxes Grading Module (BGM) and Informative Boosting Module (IBM). BGM generates proposals of the bounding boxes by using standard one-stage weakly-supervised methods, then utilizes Inclusion Principle to pick out highly-reliable boxes and evaluate the grade of each box. With the above boxes and their grade information, an effective anchor generator and a grade-aware loss are carefully designed to train the IBM. Taking the advantages of the grade information, our GradingNet achieves state-of-the-art performance on COCO, VOC 2007 and VOC 2012 benchmarks.

Downloads

Next from AAAI 2021

Anticipating Future Relations via Graph Growing for Action Prediction

Similar lecture

Activity Image-to-Video Retrieval by Disentangling Appearance and Motion

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

Anticipating Future Relations via Graph Growing for Action Prediction

Similar lecture

Activity Image-to-Video Retrieval by Disentangling Appearance and Motion

Downloads