The large amounts of data associated with 360-degree video require highly effective compression techniques for efficient storage and distribution. The development of improved motion models for 360-degree motion compensation has shown significant improvements in compression efficiency. A geodesic motion model representing translational camera motion proved to be one of the most effective models. In this paper, we propose an improved geometry-corrected geodesic motion model that outperforms the state of the art at reduced complexity. We additionally propose the transmission of per-frame camera motion information, where prior work assumed the same camera motion for all frames of a sequence. Our approach yields average Bj{\o}ntegaard Delta rate savings of 2.27% over H.266/VVC, outperforming the original geodesic motion model by 0.32 percentage points at reduced computational complexity.
With the development of spaceflight and the exploration of extraterrestrial planets, exoplanet crater detection has gradually gained attention. However, with the current scarcity of relevant datasets, high sample background complexity, and large inter-domain differences, few existing detection models can achieve good robustness and generalization across domains by training on data with more background interference. To obtain a better robust model with better cross-domain generalization in the presence of poor data quality, we propose the SCPQ model, in which we first propose a method for fusing shallow information using attention mechanism (FSIAM), which utilizes feature maps fused with deep convolved feature maps after fully extracting the global sensory field of shallow information via the attention mechanism module, which can fully fit the data to obtain a better sense of the domain in the presence of poor data, and thus better multiscale adaptability. Secondly, we propose a pseudo-label and data augment strategy (PDAS) and a smooth hard example mining (SHEM) loss function to improve cross-domain performance. PDAS adopts high-quality pseudo-labeled data from the target domain to the finetune model, and adopts different strong and weak data enhancement strategies for different domains, which mitigates the different distribution of information inherent in the source and target domains, and obtains a better generalization effect. Meanwhile, our proposed SHEM loss function can solve the problem of poor robustness of hard examples due to partial background interference learning during the training process. The SHEM loss function can smooth this interference and has generalization while learning hard examples. Experimental results show that we achieved better performance on the DACD dataset and improved the Recall of cross-domain detection by 24.04\% over baseline.
We propose a novel Attentional Scale Sequence Fusion based You Only Look Once (YOLO) framework (ASF-YOLO) which combines spatial and scale features for accurate and fast cell instance segmentation. Built on the YOLO segmentation framework, we employ the Scale Sequence Feature Fusion (SSFF) module to enhance the multi-scale information extraction capability of the network, and the Triple Feature Encoder (TPE) module to fuse feature maps of different scales to increase detailed information. We further introduce a Channel and Position Attention Mechanism (CPAM) to integrate both the SSFF and TPE modules, which focus on informative channels and spatial position-related small objects for improved detection and segmentation performance. Experimental validations on two cell datasets show remarkable segmentation accuracy and speed of the proposed ASF-YOLO model. It achieves a box mAP of 0.91, mask mAP of 0.887, and an inference speed of 47.3 FPS on the 2018 Data Science Bowl dataset, outperforming the state-of-the-art methods. The source code is available at https://github.com/mkang315/ASF-YOLO.
Designing robotic agents to perform open vocabulary tasks has been the long-standing goal in robotics and AI. Recently, Large Language Models (LLMs) have achieved impressive results in creating robotic agents for performing open vocabulary tasks. However, planning for these tasks in the presence of uncertainties is challenging as it requires \enquote{chain-of-thought} reasoning, aggregating information from the environment, updating state estimates, and generating actions based on the updated state estimates. In this paper, we present an interactive planning technique for partially observable tasks using LLMs. In the proposed method, an LLM is used to collect missing information from the environment using a robot and infer the state of the underlying problem from collected observations while guiding the robot to perform the required actions. We also use a fine-tuned Llama 2 model via self-instruct and compare its performance against a pre-trained LLM like GPT-4. Results are demonstrated on several tasks in simulation as well as real-world environments. A video describing our work along with some results could be found here.
Information Extraction (IE) aims to extract structural knowledge (e.g., entities, relations, events) from natural language texts, which brings challenges to existing methods due to task-specific schemas and complex text expressions. Code, as a typical kind of formalized language, is capable of describing structural knowledge under various schemas in a universal way. On the other hand, Large Language Models (LLMs) trained on both codes and texts have demonstrated powerful capabilities of transforming texts into codes, which provides a feasible solution to IE tasks. Therefore, in this paper, we propose a universal retrieval-augmented code generation framework based on LLMs, called Code4UIE, for IE tasks. Specifically, Code4UIE adopts Python classes to define task-specific schemas of various structural knowledge in a universal way. By so doing, extracting knowledge under these schemas can be transformed into generating codes that instantiate the predefined Python classes with the information in texts. To generate these codes more precisely, Code4UIE adopts the in-context learning mechanism to instruct LLMs with examples. In order to obtain appropriate examples for different tasks, Code4UIE explores several example retrieval strategies, which can retrieve examples semantically similar to the given texts. Extensive experiments on five representative IE tasks across nine datasets demonstrate the effectiveness of the Code4UIE framework.
Open-vocabulary keyword spotting (KWS), which allows users to customize keywords, has attracted increasingly more interest. However, existing methods based on acoustic models and post-processing train the acoustic model with ASR training criteria to model all phonemes, making the acoustic model under-optimized for the KWS task. To solve this problem, we propose a novel unified two-pass open-vocabulary KWS (U2-KWS) framework inspired by the two-pass ASR model U2. Specifically, we employ the CTC branch as the first stage model to detect potential keyword candidates and the decoder branch as the second stage model to validate candidates. In order to enhance any customized keywords, we redesign the U2 training procedure for U2-KWS and add keyword information by audio and text cross-attention into both branches. We perform experiments on our internal dataset and Aishell-1. The results show that U2-KWS can achieve a significant relative wake-up rate improvement of 41% compared to the traditional customized KWS systems when the false alarm rate is fixed to 0.5 times per hour.
Since Pretrained Language Models (PLMs) are the cornerstone of the most recent Information Retrieval (IR) models, the way they encode semantic knowledge is particularly important. However, little attention has been given to studying the PLMs' capability to capture hierarchical semantic knowledge. Traditionally, evaluating such knowledge encoded in PLMs relies on their performance on a task-dependent evaluation approach based on proxy tasks, such as hypernymy detection. Unfortunately, this approach potentially ignores other implicit and complex taxonomic relations. In this work, we propose a task-agnostic evaluation method able to evaluate to what extent PLMs can capture complex taxonomy relations, such as ancestors and siblings. The evaluation is based on intrinsic properties that capture the hierarchical nature of taxonomies. Our experimental evaluation shows that the lexico-semantic knowledge implicitly encoded in PLMs does not always capture hierarchical relations. We further demonstrate that the proposed properties can be injected into PLMs to improve their understanding of hierarchy. Through evaluations on taxonomy reconstruction, hypernym discovery and reading comprehension tasks, we show that the knowledge about hierarchy is moderately but not systematically transferable across tasks.
Self-supervised learning addresses the challenge encountered by many supervised methods, i.e. the requirement of large amounts of annotated data. This challenge is particularly pronounced in fields such as the electroencephalography (EEG) research domain. Self-supervised learning operates instead by utilizing pseudo-labels, which are generated by pretext tasks, to obtain a rich and meaningful data representation. In this study, we aim at introducing a dual-stream pretext task architecture that operates both in the time and frequency domains. In particular, we have examined the incorporation of the novel Frequency Similarity (FS) pretext task into two existing pretext tasks, Relative Positioning (RP) and Temporal Shuffling (TS). We assess the accuracy of these models using the Physionet Challenge 2018 (PC18) dataset in the context of the downstream task sleep stage classification. The inclusion of FS resulted in a notable improvement in downstream task accuracy, with a 1.28 percent improvement on RP and a 2.02 percent improvement on TS. Furthermore, when visualizing the learned embeddings using Uniform Manifold Approximation and Projection (UMAP), distinct clusters emerge, indicating that the learned representations carry meaningful information.
Automatic text simplification (TS) aims to automate the process of rewriting text to make it easier for people to read. A pre-requisite for TS to be useful is that it should convey information that is consistent with the meaning of the original text. However, current TS evaluation protocols assess system outputs for simplicity and meaning preservation without regard for the document context in which output sentences occur and for how people understand them. In this work, we introduce a human evaluation framework to assess whether simplified texts preserve meaning using reading comprehension questions. With this framework, we conduct a thorough human evaluation of texts by humans and by nine automatic systems. Supervised systems that leverage pre-training knowledge achieve the highest scores on the reading comprehension (RC) tasks amongst the automatic controllable TS systems. However, even the best-performing supervised system struggles with at least 14% of the questions, marking them as "unanswerable'' based on simplified content. We further investigate how existing TS evaluation metrics and automatic question-answering systems approximate the human judgments we obtained.
Image prefiltering with just noticeable distortion (JND) improves coding efficiency in a visual lossless way by filtering the perceptually redundant information prior to compression. However, real JND cannot be well modeled with inaccurate masking equations in traditional approaches or image-level subject tests in deep learning approaches. Thus, this paper proposes a fine-grained JND prefiltering dataset guided by image quality assessment for accurate block-level JND modeling. The dataset is constructed from decoded images to include coding effects and is also perceptually enhanced with block overlap and edge preservation. Furthermore, based on this dataset, we propose a lightweight JND prefiltering network, IQNet, which can be applied directly to different quantization cases with the same model and only needs 3K parameters. The experimental results show that the proposed approach to Versatile Video Coding could yield maximum/average bitrate savings of 41\%/15\% and 53\%/19\% for all-intra and low-delay P configurations, respectively, with negligible subjective quality loss. Our method demonstrates higher perceptual quality and a model size that is an order of magnitude smaller than previous deep learning methods.