Given a set of ordered pixel data in the form of an image, our goal is to perform upsampling on the data such that: the resulting resolution is improved by some factor, the final result passes the human test, having added new, believable, and realistic information and detail to the image, the time complexity for upscaling is relatively close to that of lossy upscaling implementations.
The recent advancements in large language models (LLMs) have revolutionized the field of natural language processing, progressively broadening their scope to multimodal perception and generation. However, effectively integrating listening capabilities into LLMs poses significant challenges, particularly with respect to generalizing across varied contexts and executing complex auditory tasks. In this work, we introduce WavLLM, a robust and adaptive speech large language model with dual encoders, and a prompt-aware LoRA weight adapter, optimized by a two-stage curriculum learning approach. Leveraging dual encoders, we decouple different types of speech information, utilizing a Whisper encoder to process the semantic content of speech, and a WavLM encoder to capture the unique characteristics of the speaker's identity. Within the curriculum learning framework, WavLLM first builds its foundational capabilities by optimizing on mixed elementary single tasks, followed by advanced multi-task training on more complex tasks such as combinations of the elementary tasks. To enhance the flexibility and adherence to different tasks and instructions, a prompt-aware LoRA weight adapter is introduced in the second advanced multi-task training stage. We validate the proposed model on universal speech benchmarks including tasks such as ASR, ST, SV, ER, and also apply it to specialized datasets like Gaokao English listening comprehension set for SQA, and speech Chain-of-Thought (CoT) evaluation set. Experiments demonstrate that the proposed model achieves state-of-the-art performance across a range of speech tasks on the same model size, exhibiting robust generalization capabilities in executing complex tasks using CoT approach. Furthermore, our model successfully completes Gaokao tasks without specialized training. The codes, models, audio, and Gaokao evaluation set can be accessed at \url{aka.ms/wavllm}.
Automatic legal text classification systems have been proposed in the literature to address knowledge extraction from judgments and detect their aspects. However, most of these systems are black boxes even when their models are interpretable. This may raise concerns about their trustworthiness. Accordingly, this work contributes with a system combining Natural Language Processing (NLP) with Machine Learning (ML) to classify legal texts in an explainable manner. We analyze the features involved in the decision and the threshold bifurcation values of the decision paths of tree structures and present this information to the users in natural language. This is the first work on automatic analysis of legal texts combining NLP and ML along with Explainable Artificial Intelligence techniques to automatically make the models' decisions understandable to end users. Furthermore, legal experts have validated our solution, and this knowledge has also been incorporated into the explanation process as "expert-in-the-loop" dictionaries. Experimental results on an annotated data set in law categories by jurisdiction demonstrate that our system yields competitive classification performance, with accuracy values well above 90%, and that its automatic explanations are easily understandable even to non-expert users.
Finance-related news such as Bloomberg News, CNN Business and Forbes are valuable sources of real data for market screening systems. In news, an expert shares opinions beyond plain technical analyses that include context such as political, sociological and cultural factors. In the same text, the expert often discusses the performance of different assets. Some key statements are mere descriptions of past events while others are predictions. Therefore, understanding the temporality of the key statements in a text is essential to separate context information from valuable predictions. We propose a novel system to detect the temporality of finance-related news at discourse level that combines Natural Language Processing and Machine Learning techniques, and exploits sophisticated features such as syntactic and semantic dependencies. More specifically, we seek to extract the dominant tenses of the main statements, which may be either explicit or implicit. We have tested our system on a labelled dataset of finance-related news annotated by researchers with knowledge in the field. Experimental results reveal a high detection precision compared to an alternative rule-based baseline approach. Ultimately, this research contributes to the state-of-the-art of market screening by identifying predictive knowledge for financial decision making.
Multimodal emotion recognition in conversation (MERC) and multimodal emotion-cause pair extraction (MECPE) has recently garnered significant attention. Emotions are the expression of affect or feelings; responses to specific events, thoughts, or situations are known as emotion causes. Both are like two sides of a coin, collectively describing human behaviors and intents. However, most existing works treat MERC and MECPE as separate tasks, which may result in potential challenges in integrating emotion and cause in real-world applications. In this paper, we propose a Unified Multimodal Emotion recognition and Emotion-Cause analysis framework (UniMEEC) to explore the causality and complementarity between emotion and emotion cause. Concretely, UniMEEC reformulates the MERC and MECPE tasks as two mask prediction problems, enhancing the interaction between emotion and cause. Meanwhile, UniMEEC shares the prompt learning among modalities for probing modality-specific knowledge from the Pre-trained model. Furthermore, we propose a task-specific hierarchical context aggregation to control the information flow to the task. Experiment results on four public benchmark datasets verify the model performance on MERC and MECPE tasks and achieve consistent improvements compared with state-of-the-art methods.
This paper presents a novel monocular depth estimation method, named ECFNet, for estimating high-quality monocular depth with clear edges and valid overall structure from a single RGB image. We make a thorough inquiry about the key factor that affects the edge depth estimation of the MDE networks, and come to a ratiocination that the edge information itself plays a critical role in predicting depth details. Driven by this analysis, we propose to explicitly employ the image edges as input for ECFNet and fuse the initial depths from different sources to produce the final depth. Specifically, ECFNet first uses a hybrid edge detection strategy to get the edge map and edge-highlighted image from the input image, and then leverages a pre-trained MDE network to infer the initial depths of the aforementioned three images. After that, ECFNet utilizes a layered fusion module (LFM) to fuse the initial depth, which will be further updated by a depth consistency module (DCM) to form the final estimation. Extensive experimental results on public datasets and ablation studies indicate that our method achieves state-of-the-art performance. Project page: https://zrealli.github.io/edgedepth.
This paper addresses the problem of generating lifelike holistic co-speech motions for 3D avatars, focusing on two key aspects: variability and coordination. Variability allows the avatar to exhibit a wide range of motions even with similar speech content, while coordination ensures a harmonious alignment among facial expressions, hand gestures, and body poses. We aim to achieve both with ProbTalk, a unified probabilistic framework designed to jointly model facial, hand, and body movements in speech. ProbTalk builds on the variational autoencoder (VAE) architecture and incorporates three core designs. First, we introduce product quantization (PQ) to the VAE, which enriches the representation of complex holistic motion. Second, we devise a novel non-autoregressive model that embeds 2D positional encoding into the product-quantized representation, thereby preserving essential structure information of the PQ codes. Last, we employ a secondary stage to refine the preliminary prediction, further sharpening the high-frequency details. Coupling these three designs enables ProbTalk to generate natural and diverse holistic co-speech motions, outperforming several state-of-the-art methods in qualitative and quantitative evaluations, particularly in terms of realism. Our code and model will be released for research purposes at https://feifeifeiliu.github.io/probtalk/.
Narrative reasoning relies on the understanding of eventualities in story contexts, which requires a wealth of background world knowledge. To help machines leverage such knowledge, existing solutions can be categorized into two groups. Some focus on implicitly modeling eventuality knowledge by pretraining language models (LMs) with eventuality-aware objectives. However, this approach breaks down knowledge structures and lacks interpretability. Others explicitly collect world knowledge of eventualities into structured eventuality-centric knowledge graphs (KGs). However, existing research on leveraging these knowledge sources for free-texts is limited. In this work, we propose an initial comprehensive framework called EventGround, which aims to tackle the problem of grounding free-texts to eventuality-centric KGs for contextualized narrative reasoning. We identify two critical problems in this direction: the event representation and sparsity problems. We provide simple yet effective parsing and partial information extraction methods to tackle these problems. Experimental results demonstrate that our approach consistently outperforms baseline models when combined with graph neural network (GNN) or large language model (LLM) based graph reasoning models. Our framework, incorporating grounded knowledge, achieves state-of-the-art performance while providing interpretable evidence.
Physically-based renderings contain Monte-Carlo noise, with variance that increases as the number of rays per pixel decreases. This noise, while zero-mean for good modern renderers, can have heavy tails (most notably, for scenes containing specular or refractive objects). Learned methods for restoring low fidelity renders are highly developed, because suppressing render noise means one can save compute and use fast renders with few rays per pixel. We demonstrate that a diffusion model can denoise low fidelity renders successfully. Furthermore, our method can be conditioned on a variety of natural render information, and this conditioning helps performance. Quantitative experiments show that our method is competitive with SOTA across a range of sampling rates, but current metrics slightly favor competitor methods. Qualitative examination of the reconstructions suggests that the metrics themselves may not be reliable. The image prior applied by a diffusion method strongly favors reconstructions that are "like" real images -- so have straight shadow boundaries, curved specularities, no "fireflies" and the like -- and metrics do not account for this. We show numerous examples where methods preferred by current metrics produce qualitatively weaker reconstructions than ours.
Open-vocabulary semantic segmentation (OVS) aims to segment images of arbitrary categories specified by class labels or captions. However, most previous best-performing methods, whether pixel grouping methods or region recognition methods, suffer from false matches between image features and category labels. We attribute this to the natural gap between the textual features and visual features. In this work, we rethink how to mitigate false matches from the perspective of image-to-image matching and propose a novel relation-aware intra-modal matching (RIM) framework for OVS based on visual foundation models. RIM achieves robust region classification by firstly constructing diverse image-modal reference features and then matching them with region features based on relation-aware ranking distribution. The proposed RIM enjoys several merits. First, the intra-modal reference features are better aligned, circumventing potential ambiguities that may arise in cross-modal matching. Second, the ranking-based matching process harnesses the structure information implicit in the inter-class relationships, making it more robust than comparing individually. Extensive experiments on three benchmarks demonstrate that RIM outperforms previous state-of-the-art methods by large margins, obtaining a lead of more than 10% in mIoU on PASCAL VOC benchmark.