Unsupervised Video Object Segmentation (VOS) aims at identifying the contours of primary foreground objects in videos without any prior knowledge. However, previous methods do not fully use spatial-temporal context and fail to tackle this challenging task in real-time. This motivates us to develop an efficient Long-Short Temporal Attention network (termed LSTA) for unsupervised VOS task from a holistic view. Specifically, LSTA consists of two dominant modules, i.e., Long Temporal Memory and Short Temporal Attention. The former captures the long-term global pixel relations of the past frames and the current frame, which models constantly present objects by encoding appearance pattern. Meanwhile, the latter reveals the short-term local pixel relations of one nearby frame and the current frame, which models moving objects by encoding motion pattern. To speedup the inference, the efficient projection and the locality-based sliding window are adopted to achieve nearly linear time complexity for the two light modules, respectively. Extensive empirical studies on several benchmarks have demonstrated promising performances of the proposed method with high efficiency.
Spoken language identification refers to the task of automatically predicting the spoken language in a given utterance. Conventionally, it is modeled as a speech-based language identification task. Prior techniques have been constrained to a single modality; however in the case of video data there is a wealth of other metadata that may be beneficial for this task. In this work, we propose MuSeLI, a Multimodal Spoken Language Identification method, which delves into the use of various metadata sources to enhance language identification. Our study reveals that metadata such as video title, description and geographic location provide substantial information to identify the spoken language of the multimedia recording. We conduct experiments using two diverse public datasets of YouTube videos, and obtain state-of-the-art results on the language identification task. We additionally conduct an ablation study that describes the distinct contribution of each modality for language recognition.
Autonomous Dynamic System (DS)-based algorithms hold a pivotal and foundational role in the field of Learning from Demonstration (LfD). Nevertheless, they confront the formidable challenge of striking a delicate balance between achieving precision in learning and ensuring the overall stability of the system. In response to this substantial challenge, this paper introduces a novel DS algorithm rooted in neural network technology. This algorithm not only possesses the capability to extract critical insights from demonstration data but also demonstrates the capacity to learn a candidate Lyapunov energy function that is consistent with the provided data. The model presented in this paper employs a straightforward neural network architecture that excels in fulfilling a dual objective: optimizing accuracy while simultaneously preserving global stability. To comprehensively evaluate the effectiveness of the proposed algorithm, rigorous assessments are conducted using the LASA dataset, further reinforced by empirical validation through a robotic experiment.
We introduce a multilingual speaker change detection model (USM-SCD) that can simultaneously detect speaker turns and perform ASR for 96 languages. This model is adapted from a speech foundation model trained on a large quantity of supervised and unsupervised data, demonstrating the utility of fine-tuning from a large generic foundation model for a downstream task. We analyze the performance of this multilingual speaker change detection model through a series of ablation studies. We show that the USM-SCD model can achieve more than 75% average speaker change detection F1 score across a test set that consists of data from 96 languages. On American English, the USM-SCD model can achieve an 85.8% speaker change detection F1 score across various public and internal test sets, beating the previous monolingual baseline model by 21% relative. We also show that we only need to fine-tune one-quarter of the trainable model parameters to achieve the best model performance. The USM-SCD model exhibits state-of-the-art ASR quality compared with a strong public ASR baseline, making it suitable to handle both tasks with negligible additional computational cost.
With its significant performance improvements, the deep learning paradigm has become a standard tool for modern image denoisers. While promising performance has been shown on seen noise distributions, existing approaches often suffer from generalisation to unseen noise types or general and real noise. It is understandable as the model is designed to learn paired mapping (e.g. from a noisy image to its clean version). In this paper, we instead propose to learn to disentangle the noisy image, under the intuitive assumption that different corrupted versions of the same clean image share a common latent space. A self-supervised learning framework is proposed to achieve the goal, without looking at the latent clean image. By taking two different corrupted versions of the same image as input, the proposed Multi-view Self-supervised Disentanglement (MeD) approach learns to disentangle the latent clean features from the corruptions and recover the clean image consequently. Extensive experimental analysis on both synthetic and real noise shows the superiority of the proposed method over prior self-supervised approaches, especially on unseen novel noise types. On real noise, the proposed method even outperforms its supervised counterparts by over 3 dB.
We introduce a novel training strategy for stereo matching and optical flow estimation that utilizes image-to-image translation between synthetic and real image domains. Our approach enables the training of models that excel in real image scenarios while relying solely on ground-truth information from synthetic images. To facilitate task-agnostic domain adaptation and the training of task-specific components, we introduce a bidirectional feature warping module that handles both left-right and forward-backward directions. Experimental results show competitive performance over previous domain translation-based methods, which substantiate the efficacy of our proposed framework, effectively leveraging the benefits of unsupervised domain adaptation, stereo matching, and optical flow estimation.
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge. This phenomenon poses a substantial challenge to the reliability of LLMs in real-world scenarios. In this paper, we survey recent efforts on the detection, explanation, and mitigation of hallucination, with an emphasis on the unique challenges posed by LLMs. We present taxonomies of the LLM hallucination phenomena and evaluation benchmarks, analyze existing approaches aiming at mitigating LLM hallucination, and discuss potential directions for future research.
In this paper, we introduce a novel approach to fine-grained cross-view geo-localization. Our method aligns a warped ground image with a corresponding GPS-tagged satellite image covering the same area using homography estimation. We first employ a differentiable spherical transform, adhering to geometric principles, to accurately align the perspective of the ground image with the satellite map. This transformation effectively places ground and aerial images in the same view and on the same plane, reducing the task to an image alignment problem. To address challenges such as occlusion, small overlapping range, and seasonal variations, we propose a robust correlation-aware homography estimator to align similar parts of the transformed ground image with the satellite image. Our method achieves sub-pixel resolution and meter-level GPS accuracy by mapping the center point of the transformed ground image to the satellite image using a homography matrix and determining the orientation of the ground camera using a point above the central axis. Operating at a speed of 30 FPS, our method outperforms state-of-the-art techniques, reducing the mean metric localization error by 21.3% and 32.4% in same-area and cross-area generalization tasks on the VIGOR benchmark, respectively, and by 34.4% on the KITTI benchmark in same-area evaluation.
Multi-Object Tracking (MOT) is a crucial computer vision task that aims to predict the bounding boxes and identities of objects simultaneously. While state-of-the-art methods have made remarkable progress by jointly optimizing the multi-task problems of detection and Re-ID feature learning, yet, few approaches explore to tackle the occlusion issue, which is a long-standing challenge in the MOT field. Generally, occluded objects may hinder the detector from estimating the bounding boxes, resulting in fragmented trajectories. And the learned occluded Re-ID embeddings are less distinct since they contain interferer. To this end, we propose an occlusion-aware detection and Re-ID calibrated network for multi-object tracking, termed as ORCTrack. Specifically, we propose an Occlusion-Aware Attention (OAA) module in the detector that highlights the object features while suppressing the occluded background regions. OAA can serve as a modulator that enhances the detector for some potentially occluded objects. Furthermore, we design a Re-ID embedding matching block based on the optimal transport problem, which focuses on enhancing and calibrating the Re-ID representations through different adjacent frames complementarily. To validate the effectiveness of the proposed method, extensive experiments are conducted on two challenging VisDrone2021-MOT and KITTI benchmarks. Experimental evaluations demonstrate the superiority of our approach, which can achieve new state-of-the-art performance and enjoy high run-time efficiency.
Multi-task learning (MTL), a learning paradigm to learn multiple related tasks simultaneously, has achieved great success in various fields. However, task-balancing remains a significant challenge in MTL, with the disparity in loss/gradient scales often leading to performance compromises. In this paper, we propose a Scale-Invariant Multi-Task Learning (SI-MTL) method to alleviate the task-balancing problem from both loss and gradient perspectives. Specifically, SI-MTL contains a logarithm transformation which is performed on all task losses to ensure scale-invariant at the loss level, and a gradient balancing method, SI-G, which normalizes all task gradients to the same magnitude as the maximum gradient norm. Extensive experiments conducted on several benchmark datasets consistently demonstrate the effectiveness of SI-G and the state-of-the-art performance of SI-MTL.