Research in the area of Vision and Language encompasses challenging topics that seek to connect visual and textual information. The video-to-text problem is one of these topics, in which the goal is to connect an input video with its textual description. This connection can be mainly made by retrieving the most significant descriptions from a corpus or generating a new one given a context video. These two ways represent essential tasks for Computer Vision and Natural Language Processing communities, called text retrieval from video task and video captioning/description task. These two tasks are substantially more complex than predicting or retrieving a single sentence from an image. The spatiotemporal information present in videos introduces diversity and complexity regarding the visual content and the structure of associated language descriptions. This review categorizes and describes the state-of-the-art techniques for the video-to-text problem. It covers the main video-to-text methods and the ways to evaluate their performance. We analyze how the most reported benchmark datasets have been created, showing their drawbacks and strengths for the problem requirements. We also show the impressive progress that researchers have made on each dataset, and we analyze why, despite this progress, the video-to-text conversion is still unsolved. State-of-the-art techniques are still a long way from achieving human-like performance in generating or retrieving video descriptions. We cover several significant challenges in the field and discuss future research directions.
Entity linking (EL) for the rapidly growing short text (e.g. search queries and news titles) is critical to industrial applications. Most existing approaches relying on adequate context for long text EL are not effective for the concise and sparse short text. In this paper, we propose a novel framework called Multi-turn Multiple-choice Machine reading comprehension (M3}) to solve the short text EL from a new perspective: a query is generated for each ambiguous mention exploiting its surrounding context, and an option selection module is employed to identify the golden entity from candidates using the query. In this way, M3 framework sufficiently interacts limited context with candidate entities during the encoding process, as well as implicitly considers the dissimilarities inside the candidate bunch in the selection stage. In addition, we design a two-stage verifier incorporated into M3 to address the commonly existed unlinkable problem in short text. To further consider the topical coherence and interdependence among referred entities, M3 leverages a multi-turn fashion to deal with mentions in a sequence manner by retrospecting historical cues. Evaluation shows that our M3 framework achieves the state-of-the-art performance on five Chinese and English datasets for the real-world short text EL.
End-to-end speech translation aims to translate speech in one language into text in another language via an end-to-end way. Most existing methods employ an encoder-decoder structure with a single encoder to learn acoustic representation and semantic information simultaneously, which ignores the speech-and-text modality differences and makes the encoder overloaded, leading to great difficulty in learning such a model. To address these issues, we propose a Speech-to-Text Adaptation for Speech Translation (STAST) model which aims to improve the end-to-end model performance by bridging the modality gap between speech and text. Specifically, we decouple the speech translation encoder into three parts and introduce a shrink mechanism to match the length of speech representation with that of the corresponding text transcription. To obtain better semantic representation, we completely integrate a text-based translation model into the STAST so that two tasks can be trained in the same latent space. Furthermore, we introduce a cross-modal adaptation method to close the distance between speech and text representation. Experimental results on English-French and English-German speech translation corpora have shown that our model significantly outperforms strong baselines, and achieves the new state-of-the-art performance.
Neural text generation models are typically trained by maximizing log-likelihood with the sequence cross entropy loss, which encourages an exact token-by-token match between a target sequence with a generated sequence. Such training objective is sub-optimal when the target sequence not perfect, e.g., when the target sequence is corrupted with noises, or when only weak sequence supervision is available. To address this challenge, we propose a novel Edit-Invariant Sequence Loss (EISL), which computes the matching loss of a target n-gram with all n-grams in the generated sequence. EISL draws inspirations from convolutional networks (ConvNets) which are shift-invariant to images, hence is robust to the shift of n-grams to tolerate edits in the target sequences. Moreover, the computation of EISL is essentially a convolution operation with target n-grams as kernels, which is easy to implement with existing libraries. To demonstrate the effectiveness of EISL, we conduct experiments on three tasks: machine translation with noisy target sequences, unsupervised text style transfer, and non-autoregressive machine translation. Experimental results show our method significantly outperforms cross entropy loss on these three tasks.
Object proposal technique with dense anchoring scheme for scene text detection were applied frequently to achieve high recall. It results in the significant improvement in accuracy but waste of computational searching, regression and classification. In this paper, we propose an anchor selection-based region proposal network (AS-RPN) using effective selected anchors instead of dense anchors to extract text proposals. The center, scales, aspect ratios and orientations of anchors are learnable instead of fixing, which leads to high recall and greatly reduced numbers of anchors. By replacing the anchor-based RPN in Faster RCNN, the AS-RPN-based Faster RCNN can achieve comparable performance with previous state-of-the-art text detecting approaches on standard benchmarks, including COCO-Text, ICDAR2013, ICDAR2015 and MSRA-TD500 when using single-scale and single model (ResNet50) testing only.
The development of active and passive biometric authentication and identification technology plays an increasingly important role in cybersecurity. Keystroke dynamics can be used to analyze the way that a user types based on various keyboard input. Previous work has shown that user authentication and classification can be achieved based on keystroke dynamics. In this research, we consider the problem of user classification based on keystroke dynamics features collected from free-text. We implement and analyze a novel a deep learning model that combines a convolutional neural network (CNN) and a gated recurrent unit (GRU). We optimize the resulting model and consider several relevant related problems. Our model is competitive with the best results obtained in previous comparable research.
Conventional methods for the image-text generation tasks mainly tackle the naturally bidirectional generation tasks separately, focusing on designing task-specific frameworks to improve the quality and fidelity of the generated samples. Recently, Vision-Language Pre-training models have greatly improved the performance of the image-to-text generation tasks, but large-scale pre-training models for text-to-image synthesis task are still under-developed. In this paper, we propose ERNIE-ViLG, a unified generative pre-training framework for bidirectional image-text generation with transformer model. Based on the image quantization models, we formulate both image generation and text generation as autoregressive generative tasks conditioned on the text/image input. The bidirectional image-text generative modeling eases the semantic alignments across vision and language. For the text-to-image generation process, we further propose an end-to-end training method to jointly learn the visual sequence generator and the image reconstructor. To explore the landscape of large-scale pre-training for bidirectional text-image generation, we train a 10-billion parameter ERNIE-ViLG model on a large-scale dataset of 145 million (Chinese) image-text pairs which achieves state-of-the-art performance for both text-to-image and image-to-text tasks, obtaining an FID of 7.9 on MS-COCO for text-to-image synthesis and best results on COCO-CN and AIC-ICC for image captioning.
In recent years, Internet memes have been widely used in online chatting. Compared with text-based communication, conversations become more expressive and attractive when Internet memes are incorporated. This paper presents our solutions for the Meme incorporated Open-domain Dialogue (MOD) Challenge of DSTC10, where three tasks are involved: text response modeling, meme retrieval, and meme emotion classification. Firstly, we leverage a large-scale pre-trained dialogue model for coherent and informative response generation. Secondly, based on interaction-based text-matching, our approach can retrieve appropriate memes with good generalization ability. Thirdly, we propose to model the emotion flow (EF) in conversations and introduce an auxiliary task of emotion description prediction (EDP) to boost the performance of meme emotion classification. Experimental results on the MOD dataset demonstrate that our methods can incorporate Internet memes into dialogue systems effectively.
Emotion classification of speech and assessment of the emotion strength are required in applications such as emotional text-to-speech and voice conversion. The emotion attribute ranking function based on Support Vector Machine (SVM) was proposed to predict emotion strength for emotional speech corpus. However, the trained ranking function doesn't generalize to new domains, which limits the scope of applications, especially for out-of-domain or unseen speech. In this paper, we propose a data-driven deep learning model, i.e. StrengthNet, to improve the generalization of emotion strength assessment for seen and unseen speech. This is achieved by the fusion of emotional data from various domains. We follow a multi-task learning network architecture that includes an acoustic encoder, a strength predictor, and an auxiliary emotion predictor. Experiments show that the predicted emotion strength of the proposed StrengthNet is highly correlated with ground truth scores for both seen and unseen speech. We release the source codes at: https://github.com/ttslr/StrengthNet.
This paper presents Lutma, a collaborative, semi-constrained, tutorial-based tool for contributing frames and lexical units to the Global FrameNet initiative. The tool parameterizes the process of frame creation, avoiding consistency violations and promoting the integration of frames contributed by the community with existing frames. Lutma is structured in a wizard-like fashion so as to provide users with text and video tutorials relevant for each step in the frame creation process. We argue that this tool will allow for a sensible expansion of FrameNet coverage in terms of both languages and cultural perspectives encoded by them, positioning frames as a viable alternative for representing perspective in language models.