Yi‐Ting Chen

Henrique Schechter Vera, Sahil Dua, Biao Zhang et al.

We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledge from larger models via encoder-decoder initialization and geometric embedding distillation. We improve model robustness and expressiveness with a spread-out regularizer, and ensure generalizability by merging checkpoints from varied, optimized mixtures. Evaluated on the Massive Text Embedding Benchmark (MTEB) across multilingual, English, and code domains, EmbeddingGemma (300M) achieves state-of-the-art results. Notably, it outperforms prior top models, both proprietary and open, with fewer than 500M parameters, and provides performance comparable to models double its size, offering an exceptional performance-to-cost ratio. Remarkably, this lead persists when quantizing model weights or truncating embedding outputs. This makes EmbeddingGemma particularly well-suited for low-latency and high-throughput use cases such as on-device applications. We provide ablation studies exploring our key design choices. We release EmbeddingGemma to the community to promote further research.

Huihui Fang, Fei Li, Huazhu Fu et al.

Age-related macular degeneration (AMD) is the leading cause of visual impairment among elderly in the world. Early detection of AMD is of great importance, as the vision loss caused by this disease is irreversible and permanent. Color fundus photography is the most cost-effective imaging modality to screen for retinal disorders. Cutting edge deep learning based algorithms have been recently developed for automatically detecting AMD from fundus images. However, there are still lack of a comprehensive annotated dataset and standard evaluation benchmarks. To deal with this issue, we set up the Automatic Detection challenge on Age-related Macular degeneration (ADAM), which was held as a satellite event of the ISBI 2020 conference. The ADAM challenge consisted of four tasks which cover the main aspects of detecting and characterizing AMD from fundus images, including detection of AMD, detection and segmentation of optic disc, localization of fovea, and detection and segmentation of lesions. As part of the challenge, we have released a comprehensive dataset of 1200 fundus images with AMD diagnostic labels, pixel-wise segmentation masks for both optic disc and AMD-related lesions (drusen, exudates, hemorrhages and scars, among others), as well as the coordinates corresponding to the location of the macular fovea. A uniform evaluation framework has been built to make a fair comparison of different models using this dataset. During the challenge, 610 results were submitted for online evaluation, with 11 teams finally participating in the onsite challenge. This paper introduces the challenge, the dataset and the evaluation methods, as well as summarizes the participating methods and analyzes their results for each task. In particular, we observed that the ensembling strategy and the incorporation of clinical domain knowledge were the key to improve the performance of the deep learning models.

Chao Jia, Yinfei Yang, Ye Xia et al.

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still rely heavily on curated training datasets that are expensive or require expert knowledge. For vision applications, representations are mostly learned using datasets with explicit class labels such as ImageNet or OpenImages. For vision-language, popular datasets like Conceptual Captions, MSCOCO, or CLIP all involve a non-trivial data collection (and cleaning) process. This costly curation process limits the size of datasets and hence hinders the scaling of trained models. In this paper, we leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps in the Conceptual Captions dataset. A simple dual-encoder architecture learns to align visual and language representations of the image and text pairs using a contrastive loss. We show that the scale of our corpus can make up for its noise and leads to state-of-the-art representations even with such a simple learning scheme. Our visual representation achieves strong performance when transferred to classification tasks such as ImageNet and VTAB. The aligned visual and language representations enables zero-shot image classification and also set new state-of-the-art results on Flickr30K and MSCOCO image-text retrieval benchmarks, even when compared with more sophisticated cross-attention models. The representations also enable cross-modality search with complex text and text + image queries.

Nakul Agarwal, Yi-Ting Chen, Behzad Dariush et al.

Spatio-temporal action localization is an important problem in computer vision that involves detecting where and when activities occur, and therefore requires modeling of both spatial and temporal features. This problem is typically formulated in the context of supervised learning, where the learned classifiers operate on the premise that both training and test data are sampled from the same underlying distribution. However, this assumption does not hold when there is a significant domain shift, leading to poor generalization performance on the test data. To address this, we focus on the hard and novel task of generalizing training models to test samples without access to any labels from the latter for spatio-temporal action localization by proposing an end-to-end unsupervised domain adaptation algorithm. We extend the state-of-the-art object detection framework to localize and classify actions. In order to minimize the domain shift, three domain adaptation modules at image level (temporal and spatial) and instance level (temporal) are designed and integrated. We design a new experimental setup and evaluate the proposed method and different adaptation modules on the UCF-Sports, UCF-101 and JHMDB benchmark datasets. We show that significant performance gain can be achieved when spatial and temporal features are adapted separately, or jointly for the most effective results.

Yi-Ting Chen, Chi-Hsuan Hsu, Chih-Han Chung et al.

In this contribution, we design, implement and evaluate the pedagogical benefits of a novel interactive note taking interface (iVRNote) in VR for the purpose of learning and reflection lectures. In future VR learning environments, students would have challenges in taking notes when they wear a head mounted display (HMD). To solve this problem, we installed a digital tablet on the desk and provided several tools in VR to facilitate the learning experience. Specifically, we track the stylus position and orientation in the physical world and then render a virtual stylus in VR. In other words, when students see a virtual stylus somewhere on the desk, they can reach out with their hand for the physical stylus. The information provided will also enable them to know where they will draw or write before the stylus touches the tablet. Since the presented iVRNote featuring our note taking system is a digital environment, we also enable students save efforts in taking extensive notes by providing several functions, such as post-editing and picture taking, so that they can pay more attention to lectures in VR. We also record the time of each stroke on the note to help students review a lecture. They can select a part of their note to revisit the corresponding segment in a virtual online lecture. Figures and the accompanying video demonstrate the feasibility of the presented iVRNote system. To evaluate the system, we conducted a user study with 20 participants to assess the preference and pedagogical benefits of the iVRNote interface.

Vasili Ramanishka, Yi-Ting Chen, Teruhisa Misu et al.

Driving Scene understanding is a key ingredient for intelligent transportation systems. To achieve systems that can operate in a complex physical and social environment, they need to understand and learn how humans drive and interact with traffic scenes. We present the Honda Research Institute Driving Dataset (HDD), a challenging dataset to enable research on learning driver behavior in real-life environments. The dataset includes 104 hours of real human driving in the San Francisco Bay Area collected using an instrumented vehicle equipped with different sensors. We provide a detailed analysis of HDD with a comparison to other driving datasets. A novel annotation methodology is introduced to enable research on driver behavior understanding from untrimmed data sequences. As the first step, baseline algorithms for driver behavior detection are trained and tested to demonstrate the feasibility of the proposed task.

Ahmed Taha, Moustafa Meshry, Xitong Yang et al.

We present a self-supervised approach using spatio-temporal signals between video frames for action recognition. A two-stream architecture is leveraged to tangle spatial and temporal representation learning. Our task is formulated as both a sequence verification and spatio-temporal alignment tasks. The former task requires motion temporal structure understanding while the latter couples the learned motion with the spatial representation. The self-supervised pre-trained weights effectiveness is validated on the action recognition task. Quantitative evaluation shows the self-supervised approach competence on three datasets: HMDB51, UCF101, and Honda driving dataset (HDD). Further investigations to boost performance and generalize validity are still required.