Jiali Yao

Yunhao Li, Qin Li, Hao Wang et al.

Current multi-object tracking (MOT) aims to predict trajectories of targets (i.e., ''where'') in videos. Yet, knowing merely ''where'' is insufficient in many crucial applications. In comparison, semantic understanding such as fine-grained behaviors, interactions, and overall summarized captions (i.e., ''what'') from videos, associated with ''where'', is highly-desired for comprehensive video analysis. Thus motivated, we introduce Semantic Multi-Object Tracking (SMOT), that aims to estimate object trajectories and meanwhile understand semantic details of associated trajectories including instance captions, instance interactions, and overall video captions, integrating ''where'' and ''what'' for tracking. In order to foster the exploration of SMOT, we propose BenSMOT, a large-scale Benchmark for Semantic MOT. Specifically, BenSMOT comprises 3,292 videos with 151K frames, covering various scenarios for semantic tracking of humans. BenSMOT provides annotations for the trajectories of targets, along with associated instance captions in natural language, instance interactions, and overall caption for each video sequence. To our best knowledge, BenSMOT is the first publicly available benchmark for SMOT. Besides, to encourage future research, we present a novel tracker named SMOTer, which is specially designed and end-to-end trained for SMOT, showing promising performance. By releasing BenSMOT, we expect to go beyond conventional MOT by predicting ''where'' and ''what'' for SMOT, opening up a new direction in tracking for video understanding. We will release BenSMOT and SMOTer at https://github.com/Nathan-Li123/SMOTer.

Xin Gu, Bing Fan, Jiali Yao et al.

In real scenarios, videos can span several minutes or even hours. However, existing research on spatio-temporal video grounding (STVG), given a textual query, mainly focuses on localizing targets in short videos of tens of seconds, typically less than one minute, which limits real-world applications. In this paper, we explore Long-Form STVG (LF-STVG), which aims to locate targets in long-term videos. Compared with short videos, long-term videos contain much longer temporal spans and more irrelevant information, making it difficult for existing STVG methods that process all frames at once. To address this challenge, we propose an AutoRegressive Transformer architecture for LF-STVG, termed ART-STVG. Unlike conventional STVG methods that require the entire video sequence to make predictions at once, ART-STVG treats the video as streaming input and processes frames sequentially, enabling efficient handling of long videos. To model spatio-temporal context, we design spatial and temporal memory banks and apply them to the decoders. Since memories from different moments are not always relevant to the current frame, we introduce simple yet effective memory selection strategies to provide more relevant information to the decoders, significantly improving performance. Furthermore, instead of parallel spatial and temporal localization, we propose a cascaded spatio-temporal design that connects the spatial decoder to the temporal decoder, allowing fine-grained spatial cues to assist complex temporal localization in long videos. Experiments on newly extended LF-STVG datasets show that ART-STVG significantly outperforms state-of-the-art methods, while achieving competitive performance on conventional short-form STVG.

Jiali Yao, Xinran Deng, Xin Gu et al.

In this paper, we propose spatio-temporal omni-object video grounding, dubbed OmniSTVG, a new STVG task that aims at localizing spatially and temporally all targets mentioned in the textual query from videos. Compared to classic STVG locating only a single target, OmniSTVG enables localization of not only an arbitrary number of text-referred targets but also their interacting counterparts in the query from the video, making it more flexible and practical in real scenarios for comprehensive understanding. In order to facilitate exploration of OmniSTVG, we introduce BOSTVG, a large-scale benchmark dedicated to OmniSTVG. Specifically, our BOSTVG consists of 10,018 videos with 10.2M frames and covers a wide selection of 287 classes from diverse scenarios. Each sequence in BOSTVG, paired with a free-form textual query, encompasses a varying number of targets ranging from 1 to 10. To ensure high quality, each video is manually annotated with meticulous inspection and refinement. To our best knowledge, BOSTVG is to date the first and the largest benchmark for OmniSTVG. To encourage future research, we introduce a simple yet effective approach, named OmniTube, which, drawing inspiration from Transformer-based STVG methods, is specially designed for OmniSTVG and demonstrates promising results. By releasing BOSTVG, we hope to go beyond classic STVG by locating every object appearing in the query for more comprehensive understanding, opening up a new direction for STVG. Our benchmark, model, and results will be released at https://github.com/JellyYao3000/OmniSTVG.

Libo Zhang, Yongsheng Yu, Jiali Yao et al.

Generative Adversarial Network (GAN) inversion have demonstrated excellent performance in image inpainting that aims to restore lost or damaged image texture using its unmasked content. Previous GAN inversion-based methods usually utilize well-trained GAN models as effective priors to generate the realistic regions for missing holes. Despite excellence, they ignore a hard constraint that the unmasked regions in the input and the output should be the same, resulting in a gap between GAN inversion and image inpainting and thus degrading the performance. Besides, existing GAN inversion approaches often consider a single modality of the input image, neglecting other auxiliary cues in images for improvements. Addressing these problems, we propose a novel GAN inversion approach, dubbed MMInvertFill, for image inpainting. MMInvertFill contains primarily a multimodal guided encoder with a pre-modulation and a GAN generator with F&W+ latent space. Specifically, the multimodal encoder aims to enhance the multi-scale structures with additional semantic segmentation edge texture modalities through a gated mask-aware attention module. Afterwards, a pre-modulation is presented to encode these structures into style vectors. To mitigate issues of conspicuous color discrepancy and semantic inconsistency, we introduce the F&W+ latent space to bridge the gap between GAN inversion and image inpainting. Furthermore, in order to reconstruct faithful and photorealistic images, we devise a simple yet effective Soft-update Mean Latent module to capture more diversified in-domain patterns for generating high-fidelity textures for massive corruptions. In our extensive experiments on six challenging datasets, we show that our MMInvertFill qualitatively and quantitatively outperforms other state-of-the-arts and it supports the completion of out-of-domain images effectively.

Tianyi Xie, Liucheng Liao, Cheng Bi et al.

The task of few-shot visual dubbing focuses on synchronizing the lip movements with arbitrary speech input for any talking head video. Albeit moderate improvements in current approaches, they commonly require high-quality homologous data sources of videos and audios, thus causing the failure to leverage heterogeneous data sufficiently. In practice, it may be intractable to collect the perfect homologous data in some cases, for example, audio-corrupted or picture-blurry videos. To explore this kind of data and support high-fidelity few-shot visual dubbing, in this paper, we novelly propose a simple yet efficient two-stage framework with a higher flexibility of mining heterogeneous data. Specifically, our two-stage paradigm employs facial landmarks as intermediate prior of latent representations and disentangles the lip movements prediction from the core task of realistic talking head generation. By this means, our method makes it possible to independently utilize the training corpus for two-stage sub-networks using more available heterogeneous data easily acquired. Besides, thanks to the disentanglement, our framework allows a further fine-tuning for a given talking head, thereby leading to better speaker-identity preserving in the final synthesized results. Moreover, the proposed method can also transfer appearance features from others to the target speaker. Extensive experimental results demonstrate the superiority of our proposed method in generating highly realistic videos synchronized with the speech over the state-of-the-art.

Mingkun Huang, Jun Zhang, Meng Cai et al.

Recurrent neural transducer (RNN-T) is a promising end-to-end (E2E) model in automatic speech recognition (ASR). It has shown superior performance compared to traditional hybrid ASR systems. However, training RNN-T from scratch is still challenging. We observe a huge gradient variance during RNN-T training and suspect it hurts the performance. In this work, we analyze the cause of the huge gradient variance in RNN-T training and proposed a new \textit{normalized jointer network} to overcome it. We also propose to enhance the RNN-T network with a modified conformer encoder network and transformer-XL predictor networks to achieve the best performance. Experiments are conducted on the open 170-hour AISHELL-1 and industrial-level 30000-hour mandarin speech dataset. On the AISHELL-1 dataset, our RNN-T system gets state-of-the-art results on AISHELL-1's streaming and non-streaming benchmark with CER 6.15\% and 5.37\% respectively. We further compare our RNN-T system with our well trained commercial hybrid system on 30000-hour-industry audio data and get 9\% relative improvement without pre-training or external language model.

Xinjian Li, Siddharth Dalmia, Juncheng Li et al.

Multilingual models can improve language processing, particularly for low resource situations, by sharing parameters across languages. Multilingual acoustic models, however, generally ignore the difference between phonemes (sounds that can support lexical contrasts in a particular language) and their corresponding phones (the sounds that are actually spoken, which are language independent). This can lead to performance degradation when combining a variety of training languages, as identically annotated phonemes can actually correspond to several different underlying phonetic realizations. In this work, we propose a joint model of both language-independent phone and language-dependent phoneme distributions. In multilingual ASR experiments over 11 languages, we find that this model improves testing performance by 2% phoneme error rate absolute in low-resource conditions. Additionally, because we are explicitly modeling language-independent phones, we can build a (nearly-)universal phone recognizer that, when combined with the PHOIBLE large, manually curated database of phone inventories, can be customized into 2,000 language dependent recognizers. Experiments on two low-resourced indigenous languages, Inuktitut and Tusom, show that our recognizer achieves phone accuracy improvements of more than 17%, moving a step closer to speech recognition for all languages in the world.

Jiali Yao, Raphael Shu, Xinjian Li et al.

The input method is an essential service on every mobile and desktop devices that provides text suggestions. It converts sequential keyboard inputs to the characters in its target language, which is indispensable for Japanese and Chinese users. Due to critical resource constraints and limited network bandwidth of the target devices, applying neural models to input method is not well explored. In this work, we apply a LSTM-based language model to input method and evaluate its performance for both prediction and conversion tasks with Japanese BCCWJ corpus. We articulate the bottleneck to be the slow softmax computation during conversion. To solve the issue, we propose incremental softmax approximation approach, which computes softmax with a selected subset vocabulary and fix the stale probabilities when the vocabulary is updated in future steps. We refer to this method as incremental selective softmax. The results show a two order speedup for the softmax computation when converting Japanese input sequences with a large vocabulary, reaching real-time speed on commodity CPU. We also exploit the model compressing potential to achieve a 92% model size reduction without losing accuracy.