Long-sequence causal reasoning seeks to uncover causal relationships within extended time series data but is hindered by complex dependencies and the challenges of validating causal links. To address the limitations of large-scale language models (e.g., GPT-4) in capturing intricate emotional causality within extended dialogues, we propose CauseMotion, a long-sequence emotional causal reasoning framework grounded in Retrieval-Augmented Generation (RAG) and multimodal fusion. Unlike conventional methods relying only on textual information, CauseMotion enriches semantic representations by incorporating audio-derived features-vocal emotion, emotional intensity, and speech rate-into textual modalities. By integrating RAG with a sliding window mechanism, it effectively retrieves and leverages contextually relevant dialogue segments, thus enabling the inference of complex emotional causal chains spanning multiple conversational turns. To evaluate its effectiveness, we constructed the first benchmark dataset dedicated to long-sequence emotional causal reasoning, featuring dialogues with over 70 turns. Experimental results demonstrate that the proposed RAG-based multimodal integrated approach, the efficacy of substantially enhances both the depth of emotional understanding and the causal inference capabilities of large-scale language models. A GLM-4 integrated with CauseMotion achieves an 8.7% improvement in causal accuracy over the original model and surpasses GPT-4o by 1.2%. Additionally, on the publicly available DiaASQ dataset, CauseMotion-GLM-4 achieves state-of-the-art results in accuracy, F1 score, and causal reasoning accuracy.

Although sign language recognition aids non-hearing-impaired understanding, many hearing-impaired individuals still rely on sign language alone due to limited literacy, underscoring the need for advanced sign language production and translation (SLP and SLT) systems. In the field of sign language production, the lack of adequate models and datasets restricts practical applications. Existing models face challenges in production accuracy and pose control, making it difficult to provide fluent sign language expressions across diverse scenarios. Additionally, data resources are scarce, particularly high-quality datasets with complete sign vocabulary and pose annotations. To address these issues, we introduce CNText2Sign and CNSign, comprehensive datasets to benchmark SLP and SLT, respectively, with CNText2Sign covering gloss and landmark mappings for SLP, and CNSign providing extensive video-to-text data for SLT. To improve the accuracy and applicability of sign language systems, we propose the AuraLLM and SignMST-C models. AuraLLM, incorporating LoRA and RAG techniques, achieves a BLEU-4 score of 50.41 on the CNText2Sign dataset, enabling precise control over gesture semantics and motion. SignMST-C employs self-supervised rapid motion video pretraining, achieving a BLEU-4 score of 31.03/32.08 on the PHOENIX2014-T benchmark, setting a new state-of-the-art. These models establish robust baselines for the datasets released for their respective tasks.

Detecting anomalies in fundus images through unsupervised methods is a challenging task due to the similarity between normal and abnormal tissues, as well as their indistinct boundaries. The current methods have limitations in accurately detecting subtle anomalies while avoiding false positives. To address these challenges, we propose the ReSynthDetect network which utilizes a reconstruction network for modeling normal images, and an anomaly generator that produces synthetic anomalies consistent with the appearance of fundus images. By combining the features of consistent anomaly generation and image reconstruction, our method is suited for detecting fundus abnormalities. The proposed approach has been extensively tested on benchmark datasets such as EyeQ and IDRiD, demonstrating state-of-the-art performance in both image-level and pixel-level anomaly detection. Our experiments indicate a substantial 9% improvement in AUROC on EyeQ and a significant 17.1% improvement in AUPR on IDRiD.

Accurate fovea localization is essential for analyzing retinal diseases to prevent irreversible vision loss. While current deep learning-based methods outperform traditional ones, they still face challenges such as the lack of local anatomical landmarks around the fovea, the inability to robustly handle diseased retinal images, and the variations in image conditions. In this paper, we propose a novel transformer-based architecture called DualStreamFoveaNet (DSFN) for multi-cue fusion. This architecture explicitly incorporates long-range connections and global features using retina and vessel distributions for robust fovea localization. We introduce a spatial attention mechanism in the dual-stream encoder to extract and fuse self-learned anatomical information, focusing more on features distributed along blood vessels and significantly reducing computational costs by decreasing token numbers. Our extensive experiments show that the proposed architecture achieves state-of-the-art performance on two public datasets and one large-scale private dataset. Furthermore, we demonstrate that the DSFN is more robust on both normal and diseased retina images and has better generalization capacity in cross-dataset experiments.

Chromosomes carry the genetic information of humans. They exhibit non-rigid and non-articulated nature with varying degrees of curvature. Chromosome straightening is an important step for subsequent karyotype construction, pathological diagnosis and cytogenetic map development. However, robust chromosome straightening remains challenging, due to the unavailability of training images, distorted chromosome details and shapes after straightening, as well as poor generalization capability. In this paper, we propose a novel architecture, ViT-Patch GAN, consisting of a self-learned motion transformation generator and a Vision Transformer-based patch (ViT-Patch) discriminator. The generator learns the motion representation of chromosomes for straightening. With the help of the ViT-Patch discriminator, the straightened chromosomes retain more shape and banding pattern details. The experimental results show that the proposed method achieves better performance on Fr\'echet Inception Distance (FID), Learned Perceptual Image Patch Similarity (LPIPS) and downstream chromosome classification accuracy, and shows excellent generalization capability on a large dataset.

Recently anomaly detection has drawn much attention in diagnosing ocular diseases. Most existing anomaly detection research in fundus images has relatively large anomaly scores in the salient retinal structures, such as blood vessels, optical cups and discs. In this paper, we propose a Region and Spatial Aware Anomaly Detection (ReSAD) method for fundus images, which obtains local region and long-range spatial information to reduce the false positives in the normal structure. ReSAD transfers a pre-trained model to extract the features of normal fundus images and applies the Region-and-Spatial-Aware feature Combination module (ReSC) for pixel-level features to build a memory bank. In the testing phase, ReSAD uses the memory bank to determine out-of-distribution samples as abnormalities. Our method significantly outperforms the existing anomaly detection methods for fundus images on two publicly benchmark datasets.

--Smooth handling of pedestrian interactions is a key requirement for Autonomous V ehicles (A V) and Advanced Driver Assistance Systems (ADAS). Such systems call for early and accurate prediction of a pedestrian's crossing/not-crossing behaviour in front of the vehicle. We stress on the necessity of early prediction for smooth operation of such systems. We introduce the influence of vehicle interactions on pedestrian intention for this purpose. In this paper, we show a discernible advance in prediction time aided by the inclusion of such vehicle interaction context. We apply our methods to two different datasets, one in-house collected - NTU dataset and another public real-life benchmark - JAAD dataset. We also propose a generic graphical model Factored Latent-Dynamic Conditional Random Fields (FLDCRF) for single and multi-label sequence prediction as well as joint interaction modeling tasks. While the existing best system predicts pedestrian stopping behaviour with 70% accuracy 0.38 seconds before the actual events, our system achieves such accuracy at least 0.9 seconds on an average before the actual events across datasets. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. S we enter the era of autonomous driving with the first ever self-driving taxi launched in December 2018, smooth handling of pedestrian interactions still remains a challenge. The tradeoff is between on-road pedestrian safety and smoothness of the ride. Recent user experiences and available online footage suggest conservative autonomous rides resulting from the emphasis on on-road pedestrian safety . T o achieve rapid user adoption, the A Vs must be able to simulate a smooth human driver-like experience without unnecessary interruptions, in addition to ensuring 100% pedestrian safety . Automated braking systems in an ADAS tackle the emergency pedestrian interactions. These brakes get activated on detecting pedestrians' crossing behaviours within the vehicle safety range. A future ADAS must be able of offer a smoother experience on such interactions. The key to a safe and smooth autonomous pedestrian interaction lies in early and accurate prediction of a pedestrian's crossing/not-crossing behaviour in front of the vehicle. Accurate and timely prediction of pedestrian behaviour ensures on-road pedestrian safety, while early anticipation of the crossing/not-crossing behaviour offers more path planning time and consequently a smoother control over the vehicle dynamics.

In this paper, we study the actor-action semantic segmentation problem, which requires joint labeling of both actor and action categories in video frames. One major challenge for this task is that when an actor performs an action, different body parts of the actor provide different types of cues for the action category and may receive inconsistent action labeling when they are labeled independently. To address this issue, we propose an end-to-end region-based actor-action segmentation approach which relies on region masks from an instance segmentation algorithm. Our main novelty is to avoid labeling pixels in a region mask independently - instead we assign a single action label to these pixels to achieve consistent action labeling. When a pixel belongs to multiple region masks, max pooling is applied to resolve labeling conflicts. Our approach uses a two-stream network as the front-end (which learns features capturing both appearance and motion information), and uses two region-based segmentation networks as the back-end (which takes the fused features from the two-stream network as the input and predicts actor-action labeling). Experiments on the A2D dataset demonstrate that both the region-based segmentation strategy and the fused features from the two-stream network contribute to the performance improvements. The proposed approach outperforms the state-of-the-art results by more than 8% in mean class accuracy, and more than 5% in mean class IOU, which validates its effectiveness.