Bringing Multimodality to Amazon Visual Search System

Image to image matching has been well studied in the computer vision community. Previous studies mainly focus on training a deep metric learning model matching visual patterns between the query image and gallery images. In this study, we show that pure image-to-image matching suffers from false positives caused by matching to local visual patterns. To alleviate this issue, we propose to leverage recent advances in vision-language pretraining research. Specifically, we introduce additional image-text alignment losses into deep metric learning, which serve as constraints to the image-to-image matching loss. With additional alignments between the text (e.g., product title) and image pairs, the model can learn concepts from both modalities explicitly, which avoids matching low-level visual features. We progressively develop two variants, a 3-tower and a 4-tower model, where the latter takes one more short text query input. Through extensive experiments, we show that this change leads to a substantial improvement to the image to image matching problem. We further leveraged this model for multimodal search, which takes both image and reformulation text queries to improve search quality. Both offline and online experiments show strong improvements on the main metrics. Specifically, we see 4.95% relative improvement on image matching click through rate with the 3-tower model and 1.13% further improvement from the 4-tower model.

Agri-LLaVA: Knowledge-Infused Large Multimodal Assistant on Agricultural Pests and Diseases

In the general domain, large multimodal models (LMMs) have achieved significant advancements, yet challenges persist in applying them to specific fields, especially agriculture. As the backbone of the global economy, agriculture confronts numerous challenges, with pests and diseases being particularly concerning due to their complexity, variability, rapid spread, and high resistance. This paper specifically addresses these issues. We construct the first multimodal instruction-following dataset in the agricultural domain, covering over 221 types of pests and diseases with approximately 400,000 data entries. This dataset aims to explore and address the unique challenges in pest and disease control. Based on this dataset, we propose a knowledge-infused training method to develop Agri-LLaVA, an agricultural multimodal conversation system. To accelerate progress in this field and inspire more researchers to engage, we design a diverse and challenging evaluation benchmark for agricultural pests and diseases. Experimental results demonstrate that Agri-LLaVA excels in agricultural multimodal conversation and visual understanding, providing new insights and approaches to address agricultural pests and diseases. By open-sourcing our dataset and model, we aim to promote research and development in LMMs within the agricultural domain and make significant contributions to tackle the challenges of agricultural pests and diseases. All resources can be found at https://github.com/Kki2Eve/Agri-LLaVA.

PlantCamo: Plant Camouflage Detection

Camouflaged Object Detection (COD) aims to detect objects with camouflaged properties. Although previous studies have focused on natural (animals and insects) and unnatural (artistic and synthetic) camouflage detection, plant camouflage has been neglected. However, plant camouflage plays a vital role in natural camouflage. Therefore, this paper introduces a new challenging problem of Plant Camouflage Detection (PCD). To address this problem, we introduce the PlantCamo dataset, which comprises 1,250 images with camouflaged plants representing 58 object categories in various natural scenes. To investigate the current status of plant camouflage detection, we conduct a large-scale benchmark study using 20+ cutting-edge COD models on the proposed dataset. Due to the unique characteristics of plant camouflage, including holes and irregular borders, we developed a new framework, named PCNet, dedicated to PCD. Our PCNet surpasses performance thanks to its multi-scale global feature enhancement and refinement. Finally, we discuss the potential applications and insights, hoping this work fills the gap in fine-grained COD research and facilitates further intelligent ecology research. All resources will be available on https://github.com/yjybuaa/PlantCamo.

Towards Unconstrained Collision Injury Protection Data Sets: Initial Surrogate Experiments for the Human Hand

Safety for physical human-robot interaction (pHRI) is a major concern for all application domains. While current standardization for industrial robot applications provide safety constraints that address the onset of pain in blunt impacts, these impact thresholds are difficult to use on edged or pointed impactors. The most severe injuries occur in constrained contact scenarios, where crushing is possible. Nevertheless, situations potentially resulting in constrained contact only occur in certain areas of a workspace and design or organisational approaches can be used to avoid them. What remains are risks to the human physical integrity caused by unconstrained accidental contacts, which are difficult to avoid while maintaining robot motion efficiency. Nevertheless, the probability and severity of injuries occurring with edged or pointed impacting objects in unconstrained collisions is hardly researched. In this paper, we propose an experimental setup and procedure using two pendulums modeling human hands and arms and robots to understand the injury potential of unconstrained collisions of human hands with edged objects. Based on our previous studies, we use pig feet as ex vivo surrogate samples - as these closely resemble the physiological characteristics of human hands - to create an initial injury database on the severity of injuries caused by unconstrained edged or pointed impacts. The use of such experimental setups and procedures in addition to other research on the occurrence of injuries in humans will eventually lead to a complete understanding of the biomechanical injury potential in pHRI.

X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs

Recent advancements in Multimodal Large Language Models (MLLMs) have revolutionized the field of vision-language understanding by integrating visual perception capabilities into Large Language Models (LLMs). The prevailing trend in this field involves the utilization of a vision encoder derived from vision-language contrastive learning (CL), showing expertise in capturing overall representations while facing difficulties in capturing detailed local patterns. In this work, we focus on enhancing the visual representations for MLLMs by combining high-frequency and detailed visual representations, obtained through masked image modeling (MIM), with semantically-enriched low-frequency representations captured by CL. To achieve this goal, we introduce X-Former which is a lightweight transformer module designed to exploit the complementary strengths of CL and MIM through an innovative interaction mechanism. Specifically, X-Former first bootstraps vision-language representation learning and multimodal-to-multimodal generative learning from two frozen vision encoders, i.e., CLIP-ViT (CL-based) and MAE-ViT (MIM-based). It further bootstraps vision-to-language generative learning from a frozen LLM to ensure visual features from X-Former can be interpreted by the LLM. To demonstrate the effectiveness of our approach, we assess its performance on tasks demanding detailed visual understanding. Extensive evaluations indicate that X-Former excels in visual reasoning tasks involving both structural and semantic categories in the GQA dataset. Assessment on fine-grained visual perception benchmark further confirms its superior capabilities in visual understanding.

PVUW 2024 Challenge on Complex Video Understanding: Methods and Results

Pixel-level Video Understanding in the Wild Challenge (PVUW) focus on complex video understanding. In this CVPR 2024 workshop, we add two new tracks, Complex Video Object Segmentation Track based on MOSE dataset and Motion Expression guided Video Segmentation track based on MeViS dataset. In the two new tracks, we provide additional videos and annotations that feature challenging elements, such as the disappearance and reappearance of objects, inconspicuous small objects, heavy occlusions, and crowded environments in MOSE. Moreover, we provide a new motion expression guided video segmentation dataset MeViS to study the natural language-guided video understanding in complex environments. These new videos, sentences, and annotations enable us to foster the development of a more comprehensive and robust pixel-level understanding of video scenes in complex environments and realistic scenarios. The MOSE challenge had 140 registered teams in total, 65 teams participated the validation phase and 12 teams made valid submissions in the final challenge phase. The MeViS challenge had 225 registered teams in total, 50 teams participated the validation phase and 5 teams made valid submissions in the final challenge phase.

1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation

Motion Expression guided Video Segmentation (MeViS), as an emerging task, poses many new challenges to the field of referring video object segmentation (RVOS). In this technical report, we investigated and validated the effectiveness of static-dominant data and frame sampling on this challenging setting. Our solution achieves a J&F score of 0.5447 in the competition phase and ranks 1st in the MeViS track of the PVUW Challenge. The code is available at: https://github.com/Tapall-AI/MeViS_Track_Solution_2024.

Place Anything into Any Video

Controllable video editing has demonstrated remarkable potential across diverse applications, particularly in scenarios where capturing or re-capturing real-world videos is either impractical or costly. This paper introduces a novel and efficient system named Place-Anything, which facilitates the insertion of any object into any video solely based on a picture or text description of the target object or element. The system comprises three modules: 3D generation, video reconstruction, and 3D target insertion. This integrated approach offers an efficient and effective solution for producing and editing high-quality videos by seamlessly inserting realistic objects. Through a user study, we demonstrate that our system can effortlessly place any object into any video using just a photograph of the object. Our demo video can be found at https://youtu.be/afXqgLLRnTE. Please also visit our project page https://place-anything.github.io to get access.

On the impact of robot personalization on human-robot interaction: A review

This study reviews the impact of personalization on human-robot interaction. Firstly, the various strategies used to achieve personalization are briefly described. Secondly, the effects of personalization known to date are discussed. They are presented along with the personalized parameters, personalized features, used technology, and use case they relate to. It is observed that various positive effects have been discussed in the literature while possible negative effects seem to require further investigation.

Track Anything: Segment Anything Meets Videos

Recently, the Segment Anything Model (SAM) gains lots of attention rapidly due to its impressive segmentation performance on images. Regarding its strong ability on image segmentation and high interactivity with different prompts, we found that it performs poorly on consistent segmentation in videos. Therefore, in this report, we propose Track Anything Model (TAM), which achieves high-performance interactive tracking and segmentation in videos. To be detailed, given a video sequence, only with very little human participation, i.e., several clicks, people can track anything they are interested in, and get satisfactory results in one-pass inference. Without additional training, such an interactive design performs impressively on video object tracking and segmentation. All resources are available on {https://github.com/gaomingqi/Track-Anything}. We hope this work can facilitate related research.