Yi Ren

Yan Xia, Zhou Zhao, Shangwei Ye et al.

In this paper, we introduce a new task, spoken video grounding (SVG), which aims to localize the desired video fragments from spoken language descriptions. Compared with using text, employing audio requires the model to directly exploit the useful phonemes and syllables related to the video from raw speech. Moreover, we randomly add environmental noises to this speech audio, further increasing the difficulty of this task and better simulating real applications. To rectify the discriminative phonemes and extract video-related information from noisy audio, we develop a novel video-guided curriculum learning (VGCL) during the audio pre-training process, which can make use of the vital visual perceptions to help understand the spoken language and suppress the external noise. Considering during inference the model can not obtain ground truth video segments, we design a curriculum strategy that gradually shifts the input video from the ground truth to the entire video content during pre-training. Finally, the model can learn how to extract critical visual information from the entire video clip to help understand the spoken language. In addition, we collect the first large-scale spoken video grounding dataset based on ActivityNet, which is named as ActivityNet Speech dataset. Extensive experiments demonstrate our proposed video-guided curriculum learning can facilitate the pre-training process to obtain a mutual audio encoder, significantly promoting the performance of spoken video grounding tasks. Moreover, we prove that in the case of noisy sound, our model outperforms the method that grounding video with ASR transcripts, further demonstrating the effectiveness of our curriculum strategy.

Changhoon Kim, Yi Ren, Yezhou Yang

Growing applications of generative models have led to new threats such as malicious personation and digital copyright infringement. One solution to these threats is model attribution, i.e., the identification of user-end models where the contents under question are generated from. Existing studies showed empirical feasibility of attribution through a centralized classifier trained on all user-end models. However, this approach is not scalable in reality as the number of models ever grows. Neither does it provide an attributability guarantee. To this end, this paper studies decentralized attribution, which relies on binary classifiers associated with each user-end model. Each binary classifier is parameterized by a user-specific key and distinguishes its associated model distribution from the authentic data distribution. We develop sufficient conditions of the keys that guarantee an attributability lower bound. Our method is validated on MNIST, CelebA, and FFHQ datasets. We also examine the trade-off between generation quality and robustness of attribution against adversarial post-processes.

Jinglin Liu, Yi Ren, Zhou Zhao et al.

Lipreading is an impressive technique and there has been a definite improvement of accuracy in recent years. However, existing methods for lipreading mainly build on autoregressive (AR) model, which generate target tokens one by one and suffer from high inference latency. To breakthrough this constraint, we propose FastLR, a non-autoregressive (NAR) lipreading model which generates all target tokens simultaneously. NAR lipreading is a challenging task that has many difficulties: 1) the discrepancy of sequence lengths between source and target makes it difficult to estimate the length of the output sequence; 2) the conditionally independent behavior of NAR generation lacks the correlation across time which leads to a poor approximation of target distribution; 3) the feature representation ability of encoder can be weak due to lack of effective alignment mechanism; and 4) the removal of AR language model exacerbates the inherent ambiguity problem of lipreading. Thus, in this paper, we introduce three methods to reduce the gap between FastLR and AR model: 1) to address challenges 1 and 2, we leverage integrate-and-fire (I\&F) module to model the correspondence between source video frames and output text sequence. 2) To tackle challenge 3, we add an auxiliary connectionist temporal classification (CTC) decoder to the top of the encoder and optimize it with extra CTC loss. We also add an auxiliary autoregressive decoder to help the feature extraction of encoder. 3) To overcome challenge 4, we propose a novel Noisy Parallel Decoding (NPD) for I\&F and bring Byte-Pair Encoding (BPE) into lipreading. Our experiments exhibit that FastLR achieves the speedup up to 10.97$\times$ comparing with state-of-the-art lipreading model with slight WER absolute increase of 1.5\% and 5.5\% on GRID and LRS2 lipreading datasets respectively, which demonstrates the effectiveness of our proposed method.

Jiaying Lu, Xin Ye, Yi Ren et al.

Multiple-choice VQA has drawn increasing attention from researchers and end-users recently. As the demand for automatically constructing large-scale multiple-choice VQA data grows, we introduce a novel task called textual Distractors Generation for VQA (DG-VQA) focusing on generating challenging yet meaningful distractors given the context image, question, and correct answer. The DG-VQA task aims at generating distractors without ground-truth training samples since such resources are rarely available. To tackle the DG-VQA unsupervisedly, we propose Gobbet, a reinforcement learning(RL) based framework that utilizes pre-trained VQA models as an alternative knowledge base to guide the distractor generation process. In Gobbet, a pre-trained VQA model serves as the environment in RL setting to provide feedback for the input multi-modal query, while a neural distractor generator serves as the agent to take actions accordingly. We propose to use existing VQA models' performance degradation as indicators of the quality of generated distractors. On the other hand, we show the utility of generated distractors through data augmentation experiments, since robustness is more and more important when AI models apply to unpredictable open-domain scenarios or security-sensitive applications. We further conduct a manual case study on the factors why distractors generated by Gobbet can fool existing models.

Xu Tan, Yi Ren, Di He et al.

Multilingual machine translation, which translates multiple languages with a single model, has attracted much attention due to its efficiency of offline training and online serving. However, traditional multilingual translation usually yields inferior accuracy compared with the counterpart using individual models for each language pair, due to language diversity and model capacity limitations. In this paper, we propose a distillation-based approach to boost the accuracy of multilingual machine translation. Specifically, individual models are first trained and regarded as teachers, and then the multilingual model is trained to fit the training data and match the outputs of individual models simultaneously through knowledge distillation. Experiments on IWSLT, WMT and Ted talk translation datasets demonstrate the effectiveness of our method. Particularly, we show that one model is enough to handle multiple languages (up to 44 languages in our experiment), with comparable or even better accuracy than individual models.