Video-text retrieval plays an essential role in multi-modal research and has been widely used in many real-world web applications. The CLIP (Contrastive Language-Image Pre-training), an image-language pre-training model, has demonstrated the power of
visual concepts learning from web collected image-text datasets. In this paper, we propose a CLIP4Clip model to transfer the knowledge of the CLIP model to video-language retrieval in an end-to-end manner. Several questions are investigated via empirical studies: 1) Whether image feature is enough for video-text retrieval? 2) How a post-pretraining on a large-scale video-text dataset based on the CLIP affect the performance? 3) What is the practical mechanism to model temporal dependency between video frames? And 4) The Hyper-parameters sensitivity of the model on video-text retrieval task. Extensive experimental results present that the CLIP4Clip model transferred from the CLIP can achieve SOTA results on various video-text retrieval datasets, including MSR-VTT, MSVC, LSMDC, ActivityNet, and DiDeMo. We release our code at https://github.com/ArrowLuo/CLIP4Clip.
Span extraction is an essential problem in machine reading comprehension. Most of the existing algorithms predict the start and end positions of an answer span in the given corresponding context by generating two probability vectors. In this paper, w
e propose a novel approach that extends the probability vector to a probability matrix. Such a matrix can cover more start-end position pairs. Precisely, to each possible start index, the method always generates an end probability vector. Besides, we propose a sampling-based training strategy to address the computational cost and memory issue in the matrix training phase. We evaluate our method on SQuAD 1.1 and three other question answering benchmarks. Leveraging the most competitive models BERT and BiDAF as the backbone, our proposed approach can get consistent improvements in all datasets, demonstrating the effectiveness of the proposed method.
In this paper, we focus on the imbalance issue, which is rarely studied in aspect term extraction and aspect sentiment classification when regarding them as sequence labeling tasks. Besides, previous works usually ignore the interaction between aspec
t terms when labeling polarities. We propose a GRadient hArmonized and CascadEd labeling model (GRACE) to solve these problems. Specifically, a cascaded labeling module is developed to enhance the interchange between aspect terms and improve the attention of sentiment tokens when labeling sentiment polarities. The polarities sequence is designed to depend on the generated aspect terms labels. To alleviate the imbalance issue, we extend the gradient harmonized mechanism used in object detection to the aspect-based sentiment analysis by adjusting the weight of each label dynamically. The proposed GRACE adopts a post-pretraining BERT as its backbone. Experimental results demonstrate that the proposed model achieves consistency improvement on multiple benchmark datasets and generates state-of-the-art results.
The detection of the abnormal area from urban data is a significant research problem. However, to the best of our knowledge, previous methods designed on spatio-temporal anomalies are road-based or grid-based, which usually causes the data sparsity p
roblem and affects the detection results. In this paper, we proposed a dynamic region partition method to address the above issues. Besides, we proposed an unsupervised REgional Anomaly Detection framework (ReAD) to detect abnormal regions with arbitrary shapes by jointly considering spatial and temporal properties. Specifically, the proposed framework first generate regions via a dynamic region partition method. It keeps that observations in the same region have adjacent locations and similar non-spatial attribute readings, and could alleviate data sparsity and heterogeneity compared with the grid-based approach. Then, an anomaly metric will be calculated for each region by a regional divergence calculation method. The abnormal regions could be finally detected by a weighted approach or a wavy approach according to the different scenario. Experiments on both the simulated dataset and real-world applications demonstrate the effectiveness and practicability of the proposed framework.
With the recent success of the pre-training technique for NLP and image-linguistic tasks, some video-linguistic pre-training works are gradually developed to improve video-text related downstream tasks. However, most of the existing multimodal models
are pre-trained for understanding tasks, leading to a pretrain-finetune discrepancy for generation tasks. This paper proposes UniVL: a Unified Video and Language pre-training model for both multimodal understanding and generation. It comprises four components, including two single-modal encoders, a cross encoder, and a decoder with the Transformer backbone. Five objectives, including video-text joint, conditioned masked language model (CMLM), conditioned masked frame model (CMFM), video-text alignment, and language reconstruction, are designed to train each of the components. We further develop two pre-training strategies, stage by stage pre-training (StagedP) and enhanced video representation (EnhancedV), to make the training process of the UniVL more effective. The pre-train is carried out on a sizeable instructional video dataset HowTo100M. Experimental results demonstrate that the UniVL can learn strong video-text representation and achieves state-of-the-art results on five downstream tasks.
This paper focuses on two related subtasks of aspect-based sentiment analysis, namely aspect term extraction and aspect sentiment classification, which we call aspect term-polarity co-extraction. The former task is to extract aspects of a product or
service from an opinion document, and the latter is to identify the polarity expressed in the document about these extracted aspects. Most existing algorithms address them as two separate tasks and solve them one by one, or only perform one task, which can be complicated for real applications. In this paper, we treat these two tasks as two sequence labeling problems and propose a novel Dual crOss-sharEd RNN framework (DOER) to generate all aspect term-polarity pairs of the input sentence simultaneously. Specifically, DOER involves a dual recurrent neural network to extract the respective representation of each task, and a cross-shared unit to consider the relationship between them. Experimental results demonstrate that the proposed framework outperforms state-of-the-art baselines on three benchmark datasets.
Aspect term extraction is one of the important subtasks in aspect-based sentiment analysis. Previous studies have shown that using dependency tree structure representation is promising for this task. However, most dependency tree structures involve o
nly one directional propagation on the dependency tree. In this paper, we first propose a novel bidirectional dependency tree network to extract dependency structure features from the given sentences. The key idea is to explicitly incorporate both representations gained separately from the bottom-up and top-down propagation on the given dependency syntactic tree. An end-to-end framework is then developed to integrate the embedded representations and BiLSTM plus CRF to learn both tree-structured and sequential features to solve the aspect term extraction problem. Experimental results demonstrate that the proposed model outperforms state-of-the-art baseline models on four benchmark SemEval datasets.
