All tables can be represented as grids. Based on this observation, we propose GridFormer, a novel approach for interpreting unconstrained table structures by predicting the vertex and edge of a grid. First, we propose a flexible table representation in the form of an MXN grid. In this representation, the vertexes and edges of the grid store the localization and adjacency information of the table. Then, we introduce a DETR-style table structure recognizer to efficiently predict this multi-objective information of the grid in a single shot. Specifically, given a set of learned row and column queries, the recognizer directly outputs the vertexes and edges information of the corresponding rows and columns. Extensive experiments on five challenging benchmarks which include wired, wireless, multi-merge-cell, oriented, and distorted tables demonstrate the competitive performance of our model over other methods.
Vectorized high-definition (HD) map is essential for autonomous driving, providing detailed and precise environmental information for advanced perception and planning. However, current map vectorization methods often exhibit deviations, and the existing evaluation metric for map vectorization lacks sufficient sensitivity to detect these deviations. To address these limitations, we propose integrating the philosophy of rasterization into map vectorization. Specifically, we introduce a new rasterization-based evaluation metric, which has superior sensitivity and is better suited to real-world autonomous driving scenarios. Furthermore, we propose MapVR (Map Vectorization via Rasterization), a novel framework that applies differentiable rasterization to vectorized outputs and then performs precise and geometry-aware supervision on rasterized HD maps. Notably, MapVR designs tailored rasterization strategies for various geometric shapes, enabling effective adaptation to a wide range of map elements. Experiments show that incorporating rasterization into map vectorization greatly enhances performance with no extra computational cost during inference, leading to more accurate map perception and ultimately promoting safer autonomous driving.
Accurate protein structure prediction can significantly accelerate the development of life science. The accuracy of AlphaFold2, a frontier end-to-end structure prediction system, is already close to that of the experimental determination techniques. Due to the complex model architecture and large memory consumption, it requires lots of computational resources and time to implement the training and inference of AlphaFold2 from scratch. The cost of running the original AlphaFold2 is expensive for most individuals and institutions. Therefore, reducing this cost could accelerate the development of life science. We implement AlphaFold2 using PaddlePaddle, namely HelixFold, to improve training and inference speed and reduce memory consumption. The performance is improved by operator fusion, tensor fusion, and hybrid parallelism computation, while the memory is optimized through Recompute, BFloat16, and memory read/write in-place. Compared with the original AlphaFold2 (implemented with Jax) and OpenFold (implemented with PyTorch), HelixFold needs only 7.5 days to complete the full end-to-end training and only 5.3 days when using hybrid parallelism, while both AlphaFold2 and OpenFold take about 11 days. HelixFold saves 1x training time. We verified that HelixFold's accuracy could be on par with AlphaFold2 on the CASP14 and CAMEO datasets. HelixFold's code is available on GitHub for free download: https://github.com/PaddlePaddle/PaddleHelix/tree/dev/apps/protein_folding/helixfold, and we also provide stable web services on https://paddlehelix.baidu.com/app/drug/protein/forecast.
Multi-modal document pre-trained models have proven to be very effective in a variety of visually-rich document understanding (VrDU) tasks. Though existing document pre-trained models have achieved excellent performance on standard benchmarks for VrDU, the way they model and exploit the interactions between vision and language on documents has hindered them from better generalization ability and higher accuracy. In this work, we investigate the problem of vision-language joint representation learning for VrDU mainly from the perspective of supervisory signals. Specifically, a pre-training paradigm called Bi-VLDoc is proposed, in which a bidirectional vision-language supervision strategy and a vision-language hybrid-attention mechanism are devised to fully explore and utilize the interactions between these two modalities, to learn stronger cross-modal document representations with richer semantics. Benefiting from the learned informative cross-modal document representations, Bi-VLDoc significantly advances the state-of-the-art performance on three widely-used document understanding benchmarks, including Form Understanding (from 85.14% to 93.44%), Receipt Information Extraction (from 96.01% to 97.84%), and Document Classification (from 96.08% to 97.12%). On Document Visual QA, Bi-VLDoc achieves the state-of-the-art performance compared to previous single model methods.
3D-aware generative models have shown that the introduction of 3D information can lead to more controllable image generation. In particular, the current state-of-the-art model GIRAFFE can control each object's rotation, translation, scale, and scene camera pose without corresponding supervision. However, GIRAFFE only operates well when the image resolution is low. We propose GIRAFFE HD, a high-resolution 3D-aware generative model that inherits all of GIRAFFE's controllable features while generating high-quality, high-resolution images ($512^2$ resolution and above). The key idea is to leverage a style-based neural renderer, and to independently generate the foreground and background to force their disentanglement while imposing consistency constraints to stitch them together to composite a coherent final image. We demonstrate state-of-the-art 3D controllable high-resolution image generation on multiple natural image datasets.
Protein-protein interactions (PPIs) are essentials for many biological processes where two or more proteins physically bind together to achieve their functions. Modeling PPIs is useful for many biomedical applications, such as vaccine design, antibody therapeutics, and peptide drug discovery. Pre-training a protein model to learn effective representation is critical for PPIs. Most pre-training models for PPIs are sequence-based, which naively adopt the language models used in natural language processing to amino acid sequences. More advanced works utilize the structure-aware pre-training technique, taking advantage of the contact maps of known protein structures. However, neither sequences nor contact maps can fully characterize structures and functions of the proteins, which are closely related to the PPI problem. Inspired by this insight, we propose a multimodal protein pre-training model with three modalities: sequence, structure, and function (S2F). Notably, instead of using contact maps to learn the amino acid-level rigid structures, we encode the structure feature with the topology complex of point clouds of heavy atoms. It allows our model to learn structural information about not only the backbones but also the side chains. Moreover, our model incorporates the knowledge from the functional description of proteins extracted from literature or manual annotations. Our experiments show that the S2F learns protein embeddings that achieve good performances on a variety of PPIs tasks, including cross-species PPI, antibody-antigen affinity prediction, antibody neutralization prediction for SARS-CoV-2, and mutation-driven binding affinity change prediction.
Proactive human-robot interaction (HRI) allows the receptionist robots to actively greet people and offer services based on vision, which has been found to improve acceptability and customer satisfaction. Existing approaches are either based on multi-stage decision processes or based on end-to-end decision models. However, the rule-based approaches require sedulous expert efforts and only handle minimal pre-defined scenarios. On the other hand, existing works with end-to-end models are limited to very general greetings or few behavior patterns (typically less than 10). To address those challenges, we propose a new end-to-end framework, the TransFormer with Visual Tokens for Human-Robot Interaction (TFVT-HRI). The proposed framework extracts visual tokens of relative objects from an RGB camera first. To ensure the correct interpretation of the scenario, a transformer decision model is then employed to process the visual tokens, which is augmented with the temporal and spatial information. It predicts the appropriate action to take in each scenario and identifies the right target. Our data is collected from an in-service receptionist robot in an office building, which is then annotated by experts for appropriate proactive behavior. The action set includes 1000+ diverse patterns by combining language, emoji expression, and body motions. We compare our model with other SOTA end-to-end models on both offline test sets and online user experiments in realistic office building environments to validate this framework. It is demonstrated that the decision model achieves SOTA performance in action triggering and selection, resulting in more humanness and intelligence when compared with the previous reactive reception policies.
As a new way of human-computer interaction, inertial sensor based in-air handwriting can provide a natural and unconstrained interaction to express more complex and richer information in 3D space. However, most of the existing in-air handwriting work is mainly focused on handwritten character recognition, which makes these work suffer from poor readability of inertial signal and lack of labeled samples. To address these two problems, we use unsupervised domain adaptation method to reconstruct the trajectory of inertial signal and generate inertial samples using online handwritten trajectories. In this paper, we propose an AirWriting Translater model to learn the bi-directional translation between trajectory domain and inertial domain in the absence of paired inertial and trajectory samples. Through semantic-level adversarial training and latent classification loss, the proposed model learns to extract domain-invariant content between inertial signal and trajectory, while preserving semantic consistency during the translation across the two domains. We carefully design the architecture, so that the proposed framework can accept inputs of arbitrary length and translate between different sampling rates. We also conduct experiments on two public datasets: 6DMG (in-air handwriting dataset) and CT (handwritten trajectory dataset), the results on the two datasets demonstrate that the proposed network successes in both Inertia-to Trajectory and Trajectory-to-Inertia translation tasks.