Keypoint detection and tracking in traditional image frames are often compromised by image quality issues such as motion blur and extreme lighting conditions. Event cameras offer potential solutions to these challenges by virtue of their high temporal resolution and high dynamic range. However, they have limited performance in practical applications due to their inherent noise in event data. This paper advocates fusing the complementary information from image frames and event streams to achieve more robust keypoint detection and tracking. Specifically, we propose a novel keypoint detection network that fuses the textural and structural information from image frames with the high-temporal-resolution motion information from event streams, namely FE-DeTr. The network leverages a temporal response consistency for supervision, ensuring stable and efficient keypoint detection. Moreover, we use a spatio-temporal nearest-neighbor search strategy for robust keypoint tracking. Extensive experiments are conducted on a new dataset featuring both image frames and event data captured under extreme conditions. The experimental results confirm the superior performance of our method over both existing frame-based and event-based methods.
相關內容
Recent advances in diffusion models can generate high-quality and stunning images from text. However, multi-turn image generation, which is of high demand in real-world scenarios, still faces challenges in maintaining semantic consistency between images and texts, as well as contextual consistency of the same subject across multiple interactive turns. To address this issue, we introduce TheaterGen, a training-free framework that integrates large language models (LLMs) and text-to-image (T2I) models to provide the capability of multi-turn image generation. Within this framework, LLMs, acting as a "Screenwriter", engage in multi-turn interaction, generating and managing a standardized prompt book that encompasses prompts and layout designs for each character in the target image. Based on these, Theatergen generate a list of character images and extract guidance information, akin to the "Rehearsal". Subsequently, through incorporating the prompt book and guidance information into the reverse denoising process of T2I diffusion models, Theatergen generate the final image, as conducting the "Final Performance". With the effective management of prompt books and character images, TheaterGen significantly improves semantic and contextual consistency in synthesized images. Furthermore, we introduce a dedicated benchmark, CMIGBench (Consistent Multi-turn Image Generation Benchmark) with 8000 multi-turn instructions. Different from previous multi-turn benchmarks, CMIGBench does not define characters in advance. Both the tasks of story generation and multi-turn editing are included on CMIGBench for comprehensive evaluation. Extensive experimental results show that TheaterGen outperforms state-of-the-art methods significantly. It raises the performance bar of the cutting-edge Mini DALLE 3 model by 21% in average character-character similarity and 19% in average text-image similarity.
In the field of image classification, existing methods often struggle with biased or ambiguous data, a prevalent issue in real-world scenarios. Current strategies, including semi-supervised learning and class blending, offer partial solutions but lack a definitive resolution. Addressing this gap, our paper introduces a novel strategy for generating high-quality labels in challenging datasets. Central to our approach is a clearly designed flowchart, based on a broad literature review, which enables the creation of reliable labels. We validate our methodology through a rigorous real-world test case in the biomedical field, specifically in deducing height reduction from vertebral imaging. Our empirical study, leveraging over 250,000 annotations, demonstrates the effectiveness of our strategies decisions compared to their alternatives.
Existing image inpainting methods have achieved remarkable accomplishments in generating visually appealing results, often accompanied by a trend toward creating more intricate structural textures. However, while these models excel at creating more realistic image content, they often leave noticeable traces of tampering, posing a significant threat to security. In this work, we take the anti-forensic capabilities into consideration, firstly proposing an end-to-end training framework for anti-forensic image inpainting named SafePaint. Specifically, we innovatively formulated image inpainting as two major tasks: semantically plausible content completion and region-wise optimization. The former is similar to current inpainting methods that aim to restore the missing regions of corrupted images. The latter, through domain adaptation, endeavors to reconcile the discrepancies between the inpainted region and the unaltered area to achieve anti-forensic goals. Through comprehensive theoretical analysis, we validate the effectiveness of domain adaptation for anti-forensic performance. Furthermore, we meticulously crafted a region-wise separated attention (RWSA) module, which not only aligns with our objective of anti-forensics but also enhances the performance of the model. Extensive qualitative and quantitative evaluations show our approach achieves comparable results to existing image inpainting methods while offering anti-forensic capabilities not available in other methods.
Emotion recognition aims to discern the emotional state of subjects within an image, relying on subject-centric and contextual visual cues. Current approaches typically follow a two-stage pipeline: first localize subjects by off-the-shelf detectors, then perform emotion classification through the late fusion of subject and context features. However, the complicated paradigm suffers from disjoint training stages and limited interaction between fine-grained subject-context elements. To address the challenge, we present a single-stage emotion recognition approach, employing a Decoupled Subject-Context Transformer (DSCT), for simultaneous subject localization and emotion classification. Rather than compartmentalizing training stages, we jointly leverage box and emotion signals as supervision to enrich subject-centric feature learning. Furthermore, we introduce DSCT to facilitate interactions between fine-grained subject-context cues in a decouple-then-fuse manner. The decoupled query token--subject queries and context queries--gradually intertwine across layers within DSCT, during which spatial and semantic relations are exploited and aggregated. We evaluate our single-stage framework on two widely used context-aware emotion recognition datasets, CAER-S and EMOTIC. Our approach surpasses two-stage alternatives with fewer parameter numbers, achieving a 3.39% accuracy improvement and a 6.46% average precision gain on CAER-S and EMOTIC datasets, respectively.
Named entity recognition (NER) is a fundamental task in natural language processing that involves identifying and classifying entities in sentences into pre-defined types. It plays a crucial role in various research fields, including entity linking, question answering, and online product recommendation. Recent studies have shown that incorporating multilingual and multimodal datasets can enhance the effectiveness of NER. This is due to language transfer learning and the presence of shared implicit features across different modalities. However, the lack of a dataset that combines multilingualism and multimodality has hindered research exploring the combination of these two aspects, as multimodality can help NER in multiple languages simultaneously. In this paper, we aim to address a more challenging task: multilingual and multimodal named entity recognition (MMNER), considering its potential value and influence. Specifically, we construct a large-scale MMNER dataset with four languages (English, French, German and Spanish) and two modalities (text and image). To tackle this challenging MMNER task on the dataset, we introduce a new model called 2M-NER, which aligns the text and image representations using contrastive learning and integrates a multimodal collaboration module to effectively depict the interactions between the two modalities. Extensive experimental results demonstrate that our model achieves the highest F1 score in multilingual and multimodal NER tasks compared to some comparative and representative baselines. Additionally, in a challenging analysis, we discovered that sentence-level alignment interferes a lot with NER models, indicating the higher level of difficulty in our dataset.
Recent advancements in subject-driven image generation have made significant strides. However, current methods still fall short in diverse application scenarios, as they require test-time tuning and cannot accept interleaved multi-image and text input. These limitations keep them far from the ultimate goal of "image as a foreign language in image generation." This paper presents Kosmos-G, a model that leverages the advanced multimodal perception capabilities of Multimodal Large Language Models (MLLMs) to tackle the aforementioned challenge. Our approach aligns the output space of MLLM with CLIP using the textual modality as an anchor and performs compositional instruction tuning on curated data. Kosmos-G demonstrates an impressive capability of zero-shot subject-driven generation with interleaved multi-image and text input. Notably, the score distillation instruction tuning requires no modifications to the image decoder. This allows for a seamless substitution of CLIP and effortless integration with a myriad of U-Net techniques ranging from fine-grained controls to personalized image decoder variants. We posit Kosmos-G as an initial attempt towards the goal of "image as a foreign language in image generation." The code can be found at //aka.ms/Kosmos-G
Current recommendation systems are significantly affected by a serious issue of temporal data shift, which is the inconsistency between the distribution of historical data and that of online data. Most existing models focus on utilizing updated data, overlooking the transferable, temporal data shift-free information that can be learned from shifting data. We propose the Temporal Invariance of Association theorem, which suggests that given a fixed search space, the relationship between the data and the data in the search space keeps invariant over time. Leveraging this principle, we designed a retrieval-based recommendation system framework that can train a data shift-free relevance network using shifting data, significantly enhancing the predictive performance of the original model in the recommendation system. However, retrieval-based recommendation models face substantial inference time costs when deployed online. To address this, we further designed a distill framework that can distill information from the relevance network into a parameterized module using shifting data. The distilled model can be deployed online alongside the original model, with only a minimal increase in inference time. Extensive experiments on multiple real datasets demonstrate that our framework significantly improves the performance of the original model by utilizing shifting data.
In mesh simplification, common requirements like accuracy, triangle quality, and feature alignment are often considered as a trade-off. Existing algorithms concentrate on just one or a few specific aspects of these requirements. For example, the well-known Quadric Error Metrics (QEM) approach prioritizes accuracy and can preserve strong feature lines/points as well but falls short in ensuring high triangle quality and may degrade weak features that are not as distinctive as strong ones. In this paper, we propose a smooth functional that simultaneously considers all of these requirements. The functional comprises a normal anisotropy term and a Centroidal Voronoi Tessellation (CVT) energy term, with the variables being a set of movable points lying on the surface. The former inherits the spirit of QEM but operates in a continuous setting, while the latter encourages even point distribution, allowing various surface metrics. We further introduce a decaying weight to automatically balance the two terms. We selected 100 CAD models from the ABC dataset, along with 21 organic models, to compare the existing mesh simplification algorithms with ours. Experimental results reveal an important observation: the introduction of a decaying weight effectively reduces the conflict between the two terms and enables the alignment of weak features. This distinctive feature sets our approach apart from most existing mesh simplification methods and demonstrates significant potential in shape understanding.
Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a threshold of 0.5) for all the labels, which completely ignores the complexity and dependencies among different labels. In this paper, we propose a meta-learning method to capture these complex label dependencies. More specifically, our method utilizes a meta-learner to jointly learn the training policies and prediction policies for different labels. The training policies are then used to train the classifier with the cross-entropy loss function, and the prediction policies are further implemented for prediction. Experimental results on fine-grained entity typing and text classification demonstrate that our proposed method can obtain more accurate multi-label classification results.
Most existing works in visual question answering (VQA) are dedicated to improving the accuracy of predicted answers, while disregarding the explanations. We argue that the explanation for an answer is of the same or even more importance compared with the answer itself, since it makes the question and answering process more understandable and traceable. To this end, we propose a new task of VQA-E (VQA with Explanation), where the computational models are required to generate an explanation with the predicted answer. We first construct a new dataset, and then frame the VQA-E problem in a multi-task learning architecture. Our VQA-E dataset is automatically derived from the VQA v2 dataset by intelligently exploiting the available captions. We have conducted a user study to validate the quality of explanations synthesized by our method. We quantitatively show that the additional supervision from explanations can not only produce insightful textual sentences to justify the answers, but also improve the performance of answer prediction. Our model outperforms the state-of-the-art methods by a clear margin on the VQA v2 dataset.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191