This paper addresses the problem of text-to-video temporal grounding, which aims to identify the time interval in a video semantically relevant to a text query. We tackle this problem using a novel regression-based model that learns to extract a collection of mid-level features for semantic phrases in a text query, which corresponds to important semantic entities described in the query (e.g., actors, objects, and actions), and reflect bi-modal interactions between the linguistic features of the query and the visual features of the video in multiple levels. The proposed method effectively predicts the target time interval by exploiting contextual information from local to global during bi-modal interactions. Through in-depth ablation studies, we find out that incorporating both local and global context in video and text interactions is crucial to the accurate grounding. Our experiment shows that the proposed method outperforms the state of the arts on Charades-STA and ActivityNet Captions datasets by large margins, 7.44\% and 4.61\% points at Recall@tIoU=0.5 metric, respectively. Code is available in https://github.com/JonghwanMun/LGI4temporalgrounding.
Auto-regressive text generation models usually focus on local fluency, and may cause inconsistent semantic meaning in long text generation. Further, automatically generating words with similar semantics is challenging, and hand-crafted linguistic rules are difficult to apply. We consider a text planning scheme and present a model-based imitation-learning approach to alleviate the aforementioned issues. Specifically, we propose a novel guider network to focus on the generative process over a longer horizon, which can assist next-word prediction and provide intermediate rewards for generator optimization. Extensive experiments demonstrate that the proposed method leads to improved performance.
This paper studies a novel pre-training technique with unpaired speech data, Speech2C, for encoder-decoder based automatic speech recognition (ASR). Within a multi-task learning framework, we introduce two pre-training tasks for the encoder-decoder network using acoustic units, i.e., pseudo codes, derived from an offline clustering model. One is to predict the pseudo codes via masked language modeling in encoder output, like HuBERT model, while the other lets the decoder learn to reconstruct pseudo codes autoregressively instead of generating textual scripts. In this way, the decoder learns to reconstruct original speech information with codes before learning to generate correct text. Comprehensive experiments on the LibriSpeech corpus show that the proposed Speech2C can relatively reduce the word error rate (WER) by 19.2% over the method without decoder pre-training, and also outperforms significantly the state-of-the-art wav2vec 2.0 and HuBERT on fine-tuning subsets of 10h and 100h.
We introduce compositional soft prompting (CSP), a parameter-efficient learning technique to improve the zero-shot compositionality of large-scale pretrained vision-language models (VLMs) without the overhead of fine-tuning the entire model. VLMs can represent arbitrary classes as natural language prompts in their flexible text encoders but they underperform state-of-the-art methods on compositional zero-shot benchmark tasks. To improve VLMs, we propose a novel form of soft prompting. We treat the attributes and objects that are composed to define classes as learnable tokens of vocabulary and tune them on multiple prompt compositions. During inference, we recompose the learned attribute-object vocabulary in new combinations and show that CSP outperforms the original VLM on benchmark datasets by an average of 14.7 percentage points of accuracy. CSP also achieves new state-of-the-art accuracies on two out of three benchmark datasets, while only fine-tuning a small number of parameters. Further, we show that CSP improves generalization to higher-order attribute-attribute-object compositions and combinations of pretrained attributes and fine-tuned objects.
Few-shot Learning (FSL) is aimed to make predictions based on a limited number of samples. Structured data such as knowledge graphs and ontology libraries has been leveraged to benefit the few-shot setting in various tasks. However, the priors adopted by the existing methods suffer from challenging knowledge missing, knowledge noise, and knowledge heterogeneity, which hinder the performance for few-shot learning. In this study, we explore knowledge injection for FSL with pre-trained language models and propose ontology-enhanced prompt-tuning (OntoPrompt). Specifically, we develop the ontology transformation based on the external knowledge graph to address the knowledge missing issue, which fulfills and converts structure knowledge to text. We further introduce span-sensitive knowledge injection via a visible matrix to select informative knowledge to handle the knowledge noise issue. To bridge the gap between knowledge and text, we propose a collective training algorithm to optimize representations jointly. We evaluate our proposed OntoPrompt in three tasks, including relation extraction, event extraction, and knowledge graph completion, with eight datasets. Experimental results demonstrate that our approach can obtain better few-shot performance than baselines.
Generative models such as the variational autoencoder (VAE) and the generative adversarial networks (GAN) have proven to be incredibly powerful for the generation of synthetic data that preserves statistical properties and utility of real-world datasets, especially in the context of image and natural language text. Nevertheless, until now, there has no successful demonstration of how to apply either method for generating useful physiological sensory data. The state-of-the-art techniques in this context have achieved only limited success. We present PHYSIOGAN, a generative model to produce high fidelity synthetic physiological sensor data readings. PHYSIOGAN consists of an encoder, decoder, and a discriminator. We evaluate PHYSIOGAN against the state-of-the-art techniques using two different real-world datasets: ECG classification and activity recognition from motion sensors datasets. We compare PHYSIOGAN to the baseline models not only the accuracy of class conditional generation but also the sample diversity and sample novelty of the synthetic datasets. We prove that PHYSIOGAN generates samples with higher utility than other generative models by showing that classification models trained on only synthetic data generated by PHYSIOGAN have only 10% and 20% decrease in their classification accuracy relative to classification models trained on the real data. Furthermore, we demonstrate the use of PHYSIOGAN for sensor data imputation in creating plausible results.
This paper introduces a high-quality rich annotated Mandarin conversational (RAMC) speech dataset called MagicData-RAMC. The MagicData-RAMC corpus contains 180 hours of conversational speech data recorded from native speakers of Mandarin Chinese over mobile phones with a sampling rate of 16 kHz. The dialogs in MagicData-RAMC are classified into 15 diversified domains and tagged with topic labels, ranging from science and technology to ordinary life. Accurate transcription and precise speaker voice activity timestamps are manually labeled for each sample. Speakers' detailed information is also provided. As a Mandarin speech dataset designed for dialog scenarios with high quality and rich annotations, MagicData-RAMC enriches the data diversity in the Mandarin speech community and allows extensive research on a series of speech-related tasks, including automatic speech recognition, speaker diarization, topic detection, keyword search, text-to-speech, etc. We also conduct several relevant tasks and provide experimental results to help evaluate the dataset.
Various models have been proposed to incorporate knowledge of syntactic structures into neural language models. However, previous works have relied heavily on elaborate components for a specific language model, usually recurrent neural network (RNN), which makes themselves unwieldy in practice to fit into other neural language models, such as Transformer and GPT-2. In this paper, we introduce the Dependency-based Mixture Language Models. In detail, we first train neural language models with a novel dependency modeling objective to learn the probability distribution of future dependent tokens given context. We then formulate the next-token probability by mixing the previous dependency modeling probability distributions with self-attention. Extensive experiments and human evaluations show that our method can be easily and effectively applied to different neural language models while improving neural text generation on various tasks.
In this paper, we investigate the problem of retrieving images from a database based on a multi-modal (image-text) query. Specifically, the query text prompts some modification in the query image and the task is to retrieve images with the desired modifications. For instance, a user of an E-Commerce platform is interested in buying a dress, which should look similar to her friend's dress, but the dress should be of white color with a ribbon sash. In this case, we would like the algorithm to retrieve some dresses with desired modifications in the query dress. We propose an autoencoder based model, ComposeAE, to learn the composition of image and text query for retrieving images. We adopt a deep metric learning approach and learn a metric that pushes composition of source image and text query closer to the target images. We also propose a rotational symmetry constraint on the optimization problem. Our approach is able to outperform the state-of-the-art method TIRG \cite{TIRG} on three benchmark datasets, namely: MIT-States, Fashion200k and Fashion IQ. In order to ensure fair comparison, we introduce strong baselines by enhancing TIRG method. To ensure reproducibility of the results, we publish our code here: \url{https://anonymous.4open.science/r/d1babc3c-0e72-448a-8594-b618bae876dc/}.
In recent years , there has been an upsurge in a new form of entertainment medium called memes. These memes although seemingly innocuous have transcended onto the boundary of online harassment against women and created an unwanted bias against them . To help alleviate this problem , we propose an early fusion model for prediction and identification of misogynistic memes and its type in this paper for which we participated in SemEval-2022 Task 5 . The model receives as input meme image with its text transcription with a target vector. Given that a key challenge with this task is the combination of different modalities to predict misogyny, our model relies on pretrained contextual representations from different state-of-the-art transformer-based language models and pretrained image pretrained models to get an effective image representation. Our model achieved competitive results on both SubTask-A and SubTask-B with the other competition teams and significantly outperforms the baselines.