In the realm of video object segmentation (VOS), the challenge of operating under low-light conditions persists, resulting in notably degraded image quality and compromised accuracy when comparing query and memory frames for similarity computation. Event cameras, characterized by their high dynamic range and ability to capture motion information of objects, offer promise in enhancing object visibility and aiding VOS methods under such low-light conditions. This paper introduces a pioneering framework tailored for low-light VOS, leveraging event camera data to elevate segmentation accuracy. Our approach hinges on two pivotal components: the Adaptive Cross-Modal Fusion (ACMF) module, aimed at extracting pertinent features while fusing image and event modalities to mitigate noise interference, and the Event-Guided Memory Matching (EGMM) module, designed to rectify the issue of inaccurate matching prevalent in low-light settings. Additionally, we present the creation of a synthetic LLE-DAVIS dataset and the curation of a real-world LLE-VOS dataset, encompassing frames and events. Experimental evaluations corroborate the efficacy of our method across both datasets, affirming its effectiveness in low-light scenarios.
In this paper, we study how well human speech can automatically be filtered when this overlaps with the voice and fan noise of a social robot, Pepper. We ultimately aim for an HRI scenario where the microphone can remain open when the robot is speaking, enabling a more natural turn-taking scheme where the human can interrupt the robot. To respond appropriately, the robot would need to understand what the interlocutor said in the overlapping part of the speech, which can be accomplished by target speech extraction (TSE). To investigate how well TSE can be accomplished in the context of the popular social robot Pepper, we set out to manufacture a datase composed of a mixture of recorded speech of Pepper itself, its fan noise (which is close to the microphones), and human speech as recorded by the Pepper microphone, in a room with low reverberation and high reverberation. Comparing a signal processing approach, with and without post-filtering, and a convolutional recurrent neural network (CRNN) approach to a state-of-the-art speaker identification-based TSE model, we found that the signal processing approach without post-filtering yielded the best performance in terms of Word Error Rate on the overlapping speech signals with low reverberation, while the CRNN approach is more robust for reverberation. These results show that estimating the human voice in overlapping speech with a robot is possible in real-life application, provided that the room reverberation is low and the human speech has a high volume or high pitch.
In this paper, a hybrid video compression framework is proposed that serves as a demonstrative showcase of deep learning-based approaches extending beyond the confines of traditional coding methodologies. The proposed hybrid framework is founded upon the Enhanced Compression Model (ECM), which is a further enhancement of the Versatile Video Coding (VVC) standard. We have augmented the latest ECM reference software with well-designed coding techniques, including block partitioning, deep learning-based loop filter, and the activation of block importance mapping (BIM) which was integrated but previously inactive within ECM, further enhancing coding performance. Compared with ECM-10.0, our method achieves 6.26, 13.33, and 12.33 BD-rate savings for the Y, U, and V components under random access (RA) configuration, respectively.
Learning time-series representations for discriminative tasks has been a long-standing challenge. Current pre-training methods are limited in either unidirectional next-token prediction or randomly masked token prediction. We propose a novel architecture called Bidirectional Timely Generative Pre-trained Transformer (BiTimelyGPT), which pre-trains on time-series data by both next-token and previous-token predictions in alternating transformer layers. This pre-training task preserves original distribution and data shapes of the time-series. Additionally, the full-rank forward and backward attention matrices exhibit more expressive representation capabilities. Using biosignal data, BiTimelyGPT demonstrates superior performance in predicting neurological functionality, disease diagnosis, and physiological signs. By visualizing the attention heatmap, we observe that the pre-trained BiTimelyGPT can identify discriminative segments from time-series sequences, even more so after fine-tuning on the task.
To promote speech processing and recognition research in driving scenarios, we build on the success of the Intelligent Cockpit Speech Recognition Challenge (ICSRC) held at ISCSLP 2022 and launch the ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) Challenge. This challenge collects over 100 hours of multi-channel speech data recorded inside a new energy vehicle and 40 hours of noise for data augmentation. Two tracks, including automatic speech recognition (ASR) and automatic speech diarization and recognition (ASDR) are set up, using character error rate (CER) and concatenated minimum permutation character error rate (cpCER) as evaluation metrics, respectively. Overall, the ICMC-ASR Challenge attracts 98 participating teams and receives 53 valid results in both tracks. In the end, first-place team USTCiflytek achieves a CER of 13.16% in the ASR track and a cpCER of 21.48% in the ASDR track, showing an absolute improvement of 13.08% and 51.4% compared to our challenge baseline, respectively.
Objective: To improve survival analysis using EHR data, we aim to develop a supervised topic model called MixEHR-SurG to simultaneously integrate heterogeneous EHR data and model survival hazard. Materials and Methods: Our technical contributions are three-folds: (1) integrating EHR topic inference with Cox proportional hazards likelihood; (2) inferring patient-specific topic hyperparameters using the PheCode concepts such that each topic can be identified with exactly one PheCode-associated phenotype; (3) multi-modal survival topic inference. This leads to a highly interpretable survival and guided topic model that can infer PheCode-specific phenotype topics associated with patient mortality. We evaluated MixEHR-G using a simulated dataset and two real-world EHR datasets: the Quebec Congenital Heart Disease (CHD) data consisting of 8,211 subjects with 75,187 outpatient claim data of 1,767 unique ICD codes; the MIMIC-III consisting of 1,458 subjects with multi-modal EHR records. Results: Compared to the baselines, MixEHR-G achieved a superior dynamic AUROC for mortality prediction, with a mean AUROC score of 0.89 in the simulation dataset and a mean AUROC of 0.645 on the CHD dataset. Qualitatively, MixEHR-G associates severe cardiac conditions with high mortality risk among the CHD patients after the first heart failure hospitalization and critical brain injuries with increased mortality among the MIMIC-III patients after their ICU discharge. Conclusion: The integration of the Cox proportional hazards model and EHR topic inference in MixEHR-SurG led to not only competitive mortality prediction but also meaningful phenotype topics for systematic survival analysis. The software is available at GitHub: https://github.com/li-lab-mcgill/MixEHR-SurG.
The scarcity of labeled audio-visual datasets is a constraint for training superior audio-visual speaker diarization systems. To improve the performance of audio-visual speaker diarization, we leverage pre-trained supervised and self-supervised speech models for audio-visual speaker diarization. Specifically, we adopt supervised~(ResNet and ECAPA-TDNN) and self-supervised pre-trained models~(WavLM and HuBERT) as the speaker and audio embedding extractors in an end-to-end audio-visual speaker diarization~(AVSD) system. Then we explore the effectiveness of different frameworks, including Transformer, Conformer, and cross-attention mechanism, in the audio-visual decoder. To mitigate the degradation of performance caused by separate training, we jointly train the audio encoder, speaker encoder, and audio-visual decoder in the AVSD system. Experiments on the MISP dataset demonstrate that the proposed method achieves superior performance and obtained third place in MISP Challenge 2022.
We present a new dense simultaneous localization and mapping (SLAM) method that uses Gaussian splats as a scene representation. The new representation enables interactive-time reconstruction and photo-realistic rendering of real-world and synthetic scenes. We propose novel strategies for seeding and optimizing Gaussian splats to extend their use from multiview offline scenarios to sequential monocular RGBD input data setups. In addition, we extend Gaussian splats to encode geometry and experiment with tracking against this scene representation. Our method achieves state-of-the-art rendering quality on both real-world and synthetic datasets while being competitive in reconstruction performance and runtime.
Monocular depth estimation using Convolutional Neural Networks (CNNs) has shown impressive performance in outdoor driving scenes. However, self-supervised learning of indoor depth from monocular sequences is quite challenging for researchers because of the following two main reasons. One is the large areas of low-texture regions and the other is the complex ego-motion on indoor training datasets. In this work, our proposed method, named IndoorDepth, consists of two innovations. In particular, we first propose a novel photometric loss with improved structural similarity (SSIM) function to tackle the challenge from low-texture regions. Moreover, in order to further mitigate the issue of inaccurate ego-motion prediction, multiple photometric losses at different stages are used to train a deeper pose network with two residual pose blocks. Subsequent ablation study can validate the effectiveness of each new idea. Experiments on the NYUv2 benchmark demonstrate that our IndoorDepth outperforms the previous state-of-the-art methods by a large margin. In addition, we also validate the generalization ability of our method on ScanNet dataset. Code is availabe at https://github.com/fcntes/IndoorDepth.