Jongwoo Park

Jongwoo Park, Kumara Kahatapitiya, Donghyun Kim et al.

Vision Transformers (ViTs) have recently become the state-of-the-art across many computer vision tasks. In contrast to convolutional networks (CNNs), ViTs enable global information sharing even within shallow layers of a network, i.e., among high-resolution features. However, this perk was later overlooked with the success of pyramid architectures such as Swin Transformer, which show better performance-complexity trade-offs. In this paper, we present a simple and efficient add-on component (termed GrafT) that considers global dependencies and multi-scale information throughout the network, in both high- and low-resolution features alike. It has the flexibility of branching out at arbitrary depths and shares most of the parameters and computations of the backbone. GrafT shows consistent gains over various well-known models which includes both hybrid and pure Transformer types, both homogeneous and pyramid structures, and various self-attention methods. In particular, it largely benefits mobile-size models by providing high-level semantics. On the ImageNet-1k dataset, GrafT delivers +3.9%, +1.4%, and +1.9% top-1 accuracy improvement to DeiT-T, Swin-T, and MobileViT-XXS, respectively. Our code and models will be made available.

Kumara Kahatapitiya, Kanchana Ranasinghe, Jongwoo Park et al.

Language has become a prominent modality in computer vision with the rise of LLMs. Despite supporting long context-lengths, their effectiveness in handling long-term information gradually declines with input length. This becomes critical, especially in applications such as long-form video understanding. In this paper, we introduce a Language Repository (LangRepo) for LLMs, that maintains concise and structured information as an interpretable (i.e., all-textual) representation. Our repository is updated iteratively based on multi-scale video chunks. We introduce write and read operations that focus on pruning redundancies in text, and extracting information at various temporal scales. The proposed framework is evaluated on zero-shot visual question-answering benchmarks including EgoSchema, NExT-QA, IntentQA and NExT-GQA, showing state-of-the-art performance at its scale. Our code is available at https://github.com/kkahatapitiya/LangRepo.

Michael S. Ryoo, Honglu Zhou, Shrikant Kendre et al. · salesforce, stanford

We present xGen-MM-Vid (BLIP-3-Video): a multimodal language model for videos, particularly designed to efficiently capture temporal information over multiple frames. BLIP-3-Video takes advantage of the 'temporal encoder' in addition to the conventional visual tokenizer, which maps a sequence of tokens over multiple frames into a compact set of visual tokens. This enables BLIP3-Video to use much fewer visual tokens than its competing models (e.g., 32 vs. 4608 tokens). We explore different types of temporal encoders, including learnable spatio-temporal pooling as well as sequential models like Token Turing Machines. We experimentally confirm that BLIP-3-Video obtains video question-answering accuracies comparable to much larger state-of-the-art models (e.g., 34B), while being much smaller (i.e., 4B) and more efficient by using fewer visual tokens. The project website is at https://www.salesforceairesearch.com/opensource/xGen-MM-Vid/index.html

Jongwoo Park, Apoorv Singh, Varun Bankiti

3D visual perception tasks based on multi-camera images are essential for autonomous driving systems. Latest work in this field performs 3D object detection by leveraging multi-view images as an input and iteratively enhancing object queries (object proposals) by cross-attending multi-view features. However, individual backbone features are not updated with multi-view features and it stays as a mere collection of the output of the single-image backbone network. Therefore we propose 3M3D: A Multi-view, Multi-path, Multi-representation for 3D Object Detection where we update both multi-view features and query features to enhance the representation of the scene in both fine panoramic view and coarse global view. Firstly, we update multi-view features by multi-view axis self-attention. It will incorporate panoramic information in the multi-view features and enhance understanding of the global scene. Secondly, we update multi-view features by self-attention of the ROI (Region of Interest) windows which encodes local finer details in the features. It will help exchange the information not only along the multi-view axis but also along the other spatial dimension. Lastly, we leverage the fact of multi-representation of queries in different domains to further boost the performance. Here we use sparse floating queries along with dense BEV (Bird's Eye View) queries, which are later post-processed to filter duplicate detections. Moreover, we show performance improvements on nuScenes benchmark dataset on top of our baselines.

Xiang Li, Cristina Mata, Jongwoo Park et al.

Vision Language Models (VLMs) have recently been leveraged to generate robotic actions, forming Vision-Language-Action (VLA) models. However, directly adapting a pretrained VLM for robotic control remains challenging, particularly when constrained by a limited number of robot demonstrations. In this work, we introduce LLaRA: Large Language and Robotics Assistant, a framework that formulates robot action policy as visuo-textual conversations and enables an efficient transfer of a pretrained VLM into a powerful VLA, motivated by the success of visual instruction tuning in Computer Vision. First, we present an automated pipeline to generate conversation-style instruction tuning data for robots from existing behavior cloning datasets, aligning robotic actions with image pixel coordinates. Further, we enhance this dataset in a self-supervised manner by defining six auxiliary tasks, without requiring any additional action annotations. We show that a VLM finetuned with a limited amount of such datasets can produce meaningful action decisions for robotic control. Through experiments across multiple simulated and real-world tasks, we demonstrate that LLaRA achieves state-of-the-art performance while preserving the generalization capabilities of large language models. The code, datasets, and pretrained models are available at https://github.com/LostXine/LLaRA.

Jongwoo Park, Kanchana Ranasinghe, Kumara Kahatapitiya et al.

Long-form videos that span across wide temporal intervals are highly information redundant and contain multiple distinct events or entities that are often loosely related. Therefore, when performing long-form video question answering (LVQA), all information necessary to generate a correct response can often be contained within a small subset of frames. Recent literature leverage large language models (LLMs) in LVQA benchmarks, achieving exceptional performance, while relying on vision language models (VLMs) to convert all visual content within videos into natural language. Such VLMs often independently caption a large number of frames uniformly sampled from long videos, which is not efficient and can mostly be redundant. Motivated by this inefficiency, we propose LVNet, a modular and training-free framework featuring a novel Hierarchical Keyframe Selector (HKS) that efficiently selects a minimal set of informative frames tailored to each question. LVNet's modularity allows easy integration with existing approaches for more efficient LVQA. We achieve state-of-the-art performance among similarly configured models across four benchmark LVQA datasets: EgoSchema, NExT-QA, IntentQA, VideoMME. The code can be found at https://github.com/jongwoopark7978/LVNet

Kanchana Ranasinghe, Xiang Li, E-Ro Nguyen et al.

We present LangToMo, a vision-language-action framework structured as a dual-system architecture that uses pixel motion forecasts as intermediate representations. Our high-level System 2, an image diffusion model, generates text-conditioned pixel motion sequences from a single frame to guide robot control. Pixel motion-a universal, interpretable, and motion-centric representation-can be extracted from videos in a weakly-supervised manner, enabling diffusion model training on any video-caption data. Treating generated pixel motion as learned universal representations, our low level System 1 module translates these into robot actions via motion-to-action mapping functions, which can be either hand-crafted or learned with minimal supervision. System 2 operates as a high-level policy applied at sparse temporal intervals, while System 1 acts as a low-level policy at dense temporal intervals. This hierarchical decoupling enables flexible, scalable, and generalizable robot control under both unsupervised and supervised settings, bridging the gap between language, motion, and action. Checkout https://kahnchana.github.io/LangToMo

Anudeep Vurity, Emanuela Marasco, Raghavendra Ramachandra et al.

Finger photo Presentation Attack Detection (PAD) can significantly strengthen smartphone device security. However, these algorithms are trained to detect certain types of attacks. Furthermore, they are designed to operate on images acquired by specific capture devices, leading to poor generalization and a lack of robustness in handling the evolving nature of mobile hardware. The proposed investigation is the first to systematically analyze the performance degradation of existing deep learning PAD systems, convolutional and transformers, in cross-capture device settings. In this paper, we introduce the ColFigPhotoAttnNet architecture designed based on window attention on color channels, followed by the nested residual network as the predictor to achieve a reliable PAD. Extensive experiments using various capture devices, including iPhone13 Pro, GooglePixel 3, Nokia C5, and OnePlusOne, were carried out to evaluate the performance of proposed and existing methods on three publicly available databases. The findings underscore the effectiveness of our approach.