Multiple pedestrian tracking faces the challenge of tracking pedestrians in the presence of occlusion. Existing methods suffer from inaccurate motion estimation, appearance feature extraction, and association due to occlusion, leading to inadequate Identification F1-Score (IDF1), excessive ID switches (IDSw), and insufficient association accuracy and recall (AssA and AssR). We found that the main reason is abnormal detections caused by partial occlusion. In this paper, we suggest that the key insight is explicit motion estimation, reliable appearance features, and fair association in occlusion scenes. Specifically, we propose an adaptive occlusion-aware multiple pedestrian tracker, OccluTrack. We first introduce an abnormal motion suppression mechanism into the Kalman Filter to adaptively detect and suppress outlier motions caused by partial occlusion. Second, we propose a pose-guided re-ID module to extract discriminative part features for partially occluded pedestrians. Last, we design a new occlusion-aware association method towards fair IoU and appearance embedding distance measurement for occluded pedestrians. Extensive evaluation results demonstrate that our OccluTrack outperforms state-of-the-art methods on MOT-Challenge datasets. Particularly, the improvements on IDF1, IDSw, AssA, and AssR demonstrate the effectiveness of our OccluTrack on tracking and association performance.
The increasing availability of multi-sensor data sparks interest in multimodal self-supervised learning. However, most existing approaches learn only common representations across modalities while ignoring intra-modal training and modality-unique representations. We propose Decoupling Common and Unique Representations (DeCUR), a simple yet effective method for multimodal self-supervised learning. By distinguishing inter- and intra-modal embeddings, DeCUR is trained to integrate complementary information across different modalities. We evaluate DeCUR in three common multimodal scenarios (radar-optical, RGB-elevation, and RGB-depth), and demonstrate its consistent benefits on scene classification and semantic segmentation downstream tasks. Notably, we get straightforward improvements by transferring our pretrained backbones to state-of-the-art supervised multimodal methods without any hyperparameter tuning. Furthermore, we conduct a comprehensive explainability analysis to shed light on the interpretation of common and unique features in our multimodal approach. Codes are available at \url{https://github.com/zhu-xlab/DeCUR}.
Volumetric design, also called massing design, is the first and critical step in professional building design which is sequential in nature. As the volumetric design process is complex, the underlying sequential design process encodes valuable information for designers. Many efforts have been made to automatically generate reasonable volumetric designs, but the quality of the generated design solutions varies, and evaluating a design solution requires either a prohibitively comprehensive set of metrics or expensive human expertise. While previous approaches focused on learning only the final design instead of sequential design tasks, we propose to encode the design knowledge from a collection of expert or high-performing design sequences and extract useful representations using transformer-based models. Later we propose to utilize the learned representations for crucial downstream applications such as design preference evaluation and procedural design generation. We develop the preference model by estimating the density of the learned representations whereas we train an autoregressive transformer model for sequential design generation. We demonstrate our ideas by leveraging a novel dataset of thousands of sequential volumetric designs. Our preference model can compare two arbitrarily given design sequences and is almost 90% accurate in evaluation against random design sequences. Our autoregressive model is also capable of autocompleting a volumetric design sequence from a partial design sequence.
Cross-scene generalizable NeRF models, which can directly synthesize novel views of unseen scenes, have become a new spotlight of the NeRF field. Several existing attempts rely on increasingly end-to-end "neuralized" architectures, i.e., replacing scene representation and/or rendering modules with performant neural networks such as transformers, and turning novel view synthesis into a feed-forward inference pipeline. While those feedforward "neuralized" architectures still do not fit diverse scenes well out of the box, we propose to bridge them with the powerful Mixture-of-Experts (MoE) idea from large language models (LLMs), which has demonstrated superior generalization ability by balancing between larger overall model capacity and flexible per-instance specialization. Starting from a recent generalizable NeRF architecture called GNT, we first demonstrate that MoE can be neatly plugged in to enhance the model. We further customize a shared permanent expert and a geometry-aware consistency loss to enforce cross-scene consistency and spatial smoothness respectively, which are essential for generalizable view synthesis. Our proposed model, dubbed GNT with Mixture-of-View-Experts (GNT-MOVE), has experimentally shown state-of-the-art results when transferring to unseen scenes, indicating remarkably better cross-scene generalization in both zero-shot and few-shot settings. Our codes are available at https://github.com/VITA-Group/GNT-MOVE.
Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for training generalizable agents. To tackle the common data scarcity issue in existing vision-and-language navigation datasets, we propose an effective paradigm for generating large-scale data for learning, which applies 1200+ photo-realistic environments from HM3D and Gibson datasets and synthesizes 4.9 million instruction trajectory pairs using fully-accessible resources on the web. Importantly, we investigate the influence of each component in this paradigm on the agent's performance and study how to adequately apply the augmented data to pre-train and fine-tune an agent. Thanks to our large-scale dataset, the performance of an existing agent can be pushed up (+11% absolute with regard to previous SoTA) to a significantly new best of 80% single-run success rate on the R2R test split by simple imitation learning. The long-lasting generalization gap between navigating in seen and unseen environments is also reduced to less than 1% (versus 8% in the previous best method). Moreover, our paradigm also facilitates different models to achieve new state-of-the-art navigation results on CVDN, REVERIE, and R2R in continuous environments.
Discovering ancient agricultural terraces in desert regions is important for the monitoring of long-term climate changes on the Earth's surface. However, traditional ground surveys are both costly and limited in scale. With the increasing accessibility of aerial and satellite data, machine learning techniques bear large potential for the automatic detection and recognition of archaeological landscapes. In this paper, we propose a deep semantic model fusion method for ancient agricultural terrace detection. The input data includes aerial images and LiDAR generated terrain features in the Negev desert. Two deep semantic segmentation models, namely DeepLabv3+ and UNet, with EfficientNet backbone, are trained and fused to provide segmentation maps of ancient terraces and walls. The proposed method won the first prize in the International AI Archaeology Challenge. Codes are available at https://github.com/wangyi111/international-archaeology-ai-challenge.
Load forecasting is of great significance in the power industry as it can provide a reference for subsequent tasks such as power grid dispatch, thus bringing huge economic benefits. However, there are many differences between load forecasting and traditional time series forecasting. On the one hand, load forecasting aims to minimize the cost of subsequent tasks such as power grid dispatch, rather than simply pursuing prediction accuracy. On the other hand, the load is largely influenced by many external factors, such as temperature or calendar variables. In addition, the scale of predictions (such as building-level loads and aggregated-level loads) can also significantly impact the predicted results. In this paper, we provide a comprehensive load forecasting archive, which includes load domain-specific feature engineering to help forecasting models better model load data. In addition, different from the traditional loss function which only aims for accuracy, we also provide a method to customize the loss function based on the forecasting error, integrating it into our forecasting framework. Based on this, we conducted extensive experiments on load data at different levels, providing a reference for researchers to compare different load forecasting models.
This paper introduces InternVid, a large-scale video-centric multimodal dataset that enables learning powerful and transferable video-text representations for multimodal understanding and generation. The InternVid dataset contains over 7 million videos lasting nearly 760K hours, yielding 234M video clips accompanied by detailed descriptions of total 4.1B words. Our core contribution is to develop a scalable approach to autonomously build a high-quality video-text dataset with large language models (LLM), thereby showcasing its efficacy in learning video-language representation at scale. Specifically, we utilize a multi-scale approach to generate video-related descriptions. Furthermore, we introduce ViCLIP, a video-text representation learning model based on ViT-L. Learned on InternVid via contrastive learning, this model demonstrates leading zero-shot action recognition and competitive video retrieval performance. Beyond basic video understanding tasks like recognition and retrieval, our dataset and model have broad applications. They are particularly beneficial for generating interleaved video-text data for learning a video-centric dialogue system, advancing video-to-text and text-to-video generation research. These proposed resources provide a tool for researchers and practitioners interested in multimodal video understanding and generation.