Meta-Transformer: A Unified Framework for Multimodal Learning

Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging to design a unified network for processing various modalities ($\textit{e.g.}$ natural language, 2D images, 3D point clouds, audio, video, time series, tabular data) due to the inherent gaps among them. In this work, we propose a framework, named Meta-Transformer, that leverages a $\textbf{frozen}$ encoder to perform multimodal perception without any paired multimodal training data. In Meta-Transformer, the raw input data from various modalities are mapped into a shared token space, allowing a subsequent encoder with frozen parameters to extract high-level semantic features of the input data. Composed of three main components: a unified data tokenizer, a modality-shared encoder, and task-specific heads for downstream tasks, Meta-Transformer is the first framework to perform unified learning across 12 modalities with unpaired data. Experiments on different benchmarks reveal that Meta-Transformer can handle a wide range of tasks including fundamental perception (text, image, point cloud, audio, video), practical application (X-Ray, infrared, hyperspectral, and IMU), and data mining (graph, tabular, and time-series). Meta-Transformer indicates a promising future for developing unified multimodal intelligence with transformers. Code will be available at https://github.com/invictus717/MetaTransformer

What Can Simple Arithmetic Operations Do for Temporal Modeling?

Temporal modeling plays a crucial role in understanding video content. To tackle this problem, previous studies built complicated temporal relations through time sequence thanks to the development of computationally powerful devices. In this work, we explore the potential of four simple arithmetic operations for temporal modeling. Specifically, we first capture auxiliary temporal cues by computing addition, subtraction, multiplication, and division between pairs of extracted frame features. Then, we extract corresponding features from these cues to benefit the original temporal-irrespective domain. We term such a simple pipeline as an Arithmetic Temporal Module (ATM), which operates on the stem of a visual backbone with a plug-andplay style. We conduct comprehensive ablation studies on the instantiation of ATMs and demonstrate that this module provides powerful temporal modeling capability at a low computational cost. Moreover, the ATM is compatible with both CNNs- and ViTs-based architectures. Our results show that ATM achieves superior performance over several popular video benchmarks. Specifically, on Something-Something V1, V2 and Kinetics-400, we reach top-1 accuracy of 65.6%, 74.6%, and 89.4% respectively. The code is available at https://github.com/whwu95/ATM.

Retrieve Anyone: A General-purpose Person Re-identification Task with Instructions

Human intelligence can retrieve any person according to both visual and language descriptions. However, the current computer vision community studies specific person re-identification (ReID) tasks in different scenarios separately, which limits the applications in the real world. This paper strives to resolve this problem by proposing a new instruct-ReID task that requires the model to retrieve images according to the given image or language instructions.Our instruct-ReID is a more general ReID setting, where existing ReID tasks can be viewed as special cases by designing different instructions. We propose a large-scale OmniReID benchmark and an adaptive triplet loss as a baseline method to facilitate research in this new setting. Experimental results show that the baseline model trained on our OmniReID benchmark can improve +0.6%, +1.4%, 0.2% mAP on Market1501, CUHK03, MSMT17 for traditional ReID, +0.8%, +2.0%, +13.4% mAP on PRCC, VC-Clothes, LTCC for clothes-changing ReID, +11.7% mAP on COCAS+ real2 for clothestemplate based clothes-changing ReID when using only RGB images, +25.4% mAP on COCAS+ real2 for our newly defined language-instructed ReID. The dataset, model, and code will be available at https://github.com/hwz-zju/Instruct-ReID.

MotionGPT: Finetuned LLMs are General-Purpose Motion Generators

Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans. While recent works have achieved impressive results in generating motion directly from textual action descriptions, they often support only a single modality of the control signal, which limits their application in the real digital human industry. This paper presents a Motion General-Purpose generaTor (MotionGPT) that can use multimodal control signals, e.g., text and single-frame poses, for generating consecutive human motions by treating multimodal signals as special input tokens in large language models (LLMs). Specifically, we first quantize multimodal control signals into discrete codes and then formulate them in a unified prompt instruction to ask the LLMs to generate the motion answer. Our MotionGPT demonstrates a unified human motion generation model with multimodal control signals by tuning a mere 0.4% of LLM parameters. To the best of our knowledge, MotionGPT is the first method to generate human motion by multimodal control signals, which we hope can shed light on this new direction. Codes shall be released upon acceptance.

UniG3D: A Unified 3D Object Generation Dataset

The field of generative AI has a transformative impact on various areas, including virtual reality, autonomous driving, the metaverse, gaming, and robotics. Among these applications, 3D object generation techniques are of utmost importance. This technique has unlocked fresh avenues in the realm of creating, customizing, and exploring 3D objects. However, the quality and diversity of existing 3D object generation methods are constrained by the inadequacies of existing 3D object datasets, including issues related to text quality, the incompleteness of multi-modal data representation encompassing 2D rendered images and 3D assets, as well as the size of the dataset. In order to resolve these issues, we present UniG3D, a unified 3D object generation dataset constructed by employing a universal data transformation pipeline on Objaverse and ShapeNet datasets. This pipeline converts each raw 3D model into comprehensive multi-modal data representation <text, image, point cloud, mesh> by employing rendering engines and multi-modal models. These modules ensure the richness of textual information and the comprehensiveness of data representation. Remarkably, the universality of our pipeline refers to its ability to be applied to any 3D dataset, as it only requires raw 3D data. The selection of data sources for our dataset is based on their scale and quality. Subsequently, we assess the effectiveness of our dataset by employing Point-E and SDFusion, two widely recognized methods for object generation, tailored to the prevalent 3D representations of point clouds and signed distance functions. Our dataset is available at: https://unig3d.github.io.

LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark

Large language models have become a potential pathway toward achieving artificial general intelligence. Recent works on multi-modal large language models have demonstrated their effectiveness in handling visual modalities. In this work, we extend the research of MLLMs to point clouds and present the LAMM-Dataset and LAMM-Benchmark for 2D image and 3D point cloud understanding. We also establish an extensible framework to facilitate the extension of MLLMs to additional modalities. Our main contribution is three-fold: 1) We present the LAMM-Dataset and LAMM-Benchmark, which cover almost all high-level vision tasks for 2D and 3D vision. Extensive experiments validate the effectiveness of our dataset and benchmark. 2) We demonstrate the detailed methods of constructing instruction-tuning datasets and benchmarks for MLLMs, which will enable future research on MLLMs to scale up and extend to other domains, tasks, and modalities faster. 3) We provide a primary but potential MLLM training framework optimized for modalities' extension. We also provide baseline models, comprehensive experimental observations, and analysis to accelerate future research. Codes and datasets are now available at https://github.com/OpenLAMM/LAMM.

Adaptive Hierarchical SpatioTemporal Network for Traffic Forecasting

Accurate traffic forecasting is vital to intelligent transportation systems, which are widely adopted to solve urban traffic issues. Existing traffic forecasting studies focus on modeling spatial-temporal dynamics in traffic data, among which the graph convolution network (GCN) is at the center for exploiting the spatial dependency embedded in the road network graphs. However, these GCN-based methods operate intrinsically on the node level (e.g., road and intersection) only whereas overlooking the spatial hierarchy of the whole city. Nodes such as intersections and road segments can form clusters (e.g., regions), which could also have interactions with each other and share similarities at a higher level. In this work, we propose an Adaptive Hierarchical SpatioTemporal Network (AHSTN) to promote traffic forecasting by exploiting the spatial hierarchy and modeling multi-scale spatial correlations. Apart from the node-level spatiotemporal blocks, AHSTN introduces the adaptive spatiotemporal downsampling module to infer the spatial hierarchy for spatiotemporal modeling at the cluster level. Then, an adaptive spatiotemporal upsampling module is proposed to upsample the cluster-level representations to the node-level and obtain the multi-scale representations for generating predictions. Experiments on two real-world datasets show that AHSTN achieves better performance over several strong baselines.

Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection

LiDAR and Radar are two complementary sensing approaches in that LiDAR specializes in capturing an object's 3D shape while Radar provides longer detection ranges as well as velocity hints. Though seemingly natural, how to efficiently combine them for improved feature representation is still unclear. The main challenge arises from that Radar data are extremely sparse and lack height information. Therefore, directly integrating Radar features into LiDAR-centric detection networks is not optimal. In this work, we introduce a bi-directional LiDAR-Radar fusion framework, termed Bi-LRFusion, to tackle the challenges and improve 3D detection for dynamic objects. Technically, Bi-LRFusion involves two steps: first, it enriches Radar's local features by learning important details from the LiDAR branch to alleviate the problems caused by the absence of height information and extreme sparsity; second, it combines LiDAR features with the enhanced Radar features in a unified bird's-eye-view representation. We conduct extensive experiments on nuScenes and ORR datasets, and show that our Bi-LRFusion achieves state-of-the-art performance for detecting dynamic objects. Notably, Radar data in these two datasets have different formats, which demonstrates the generalizability of our method. Codes are available at https://github.com/JessieW0806/BiLRFusion.

PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer

Recent Transformer-based 3D object detectors learn point cloud features either from point- or voxel-based representations. However, the former requires time-consuming sampling while the latter introduces quantization errors. In this paper, we present a novel Point-Voxel Transformer for single-stage 3D detection (PVT-SSD) that takes advantage of these two representations. Specifically, we first use voxel-based sparse convolutions for efficient feature encoding. Then, we propose a Point-Voxel Transformer (PVT) module that obtains long-range contexts in a cheap manner from voxels while attaining accurate positions from points. The key to associating the two different representations is our introduced input-dependent Query Initialization module, which could efficiently generate reference points and content queries. Then, PVT adaptively fuses long-range contextual and local geometric information around reference points into content queries. Further, to quickly find the neighboring points of reference points, we design the Virtual Range Image module, which generalizes the native range image to multi-sensor and multi-frame. The experiments on several autonomous driving benchmarks verify the effectiveness and efficiency of the proposed method. Code will be available at https://github.com/Nightmare-n/PVT-SSD.

Clothes-Invariant Feature Learning by Causal Intervention for Clothes-Changing Person Re-identification

Clothes-invariant feature extraction is critical to the clothes-changing person re-identification (CC-ReID). It can provide discriminative identity features and eliminate the negative effects caused by the confounder--clothing changes. But we argue that there exists a strong spurious correlation between clothes and human identity, that restricts the common likelihood-based ReID method P(Y|X) to extract clothes-irrelevant features. In this paper, we propose a new Causal Clothes-Invariant Learning (CCIL) method to achieve clothes-invariant feature learning by modeling causal intervention P(Y|do(X)). This new causality-based model is inherently invariant to the confounder in the causal view, which can achieve the clothes-invariant features and avoid the barrier faced by the likelihood-based methods. Extensive experiments on three CC-ReID benchmarks, including PRCC, LTCC, and VC-Clothes, demonstrate the effectiveness of our approach, which achieves a new state of the art.