Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning

Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones. However, in 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling remains dominant. This raises the question: Can we take the best of both worlds? To answer this question, we first empirically validate that integrating MAE-based point cloud pre-training with the standard contrastive learning paradigm, even with meticulous design, can lead to a decrease in performance. To address this limitation, we reintroduce CL into the MAE-based point cloud pre-training paradigm by leveraging the inherent contrastive properties of MAE. Specifically, rather than relying on extensive data augmentation as commonly used in the image domain, we randomly mask the input tokens twice to generate contrastive input pairs. Subsequently, a weight-sharing encoder and two identically structured decoders are utilized to perform masked token reconstruction. Additionally, we propose that for an input token masked by both masks simultaneously, the reconstructed features should be as similar as possible. This naturally establishes an explicit contrastive constraint within the generative MAE-based pre-training paradigm, resulting in our proposed method, Point-CMAE. Consequently, Point-CMAE effectively enhances the representation quality and transfer performance compared to its MAE counterpart. Experimental evaluations across various downstream applications, including classification, part segmentation, and few-shot learning, demonstrate the efficacy of our framework in surpassing state-of-the-art techniques under standard ViTs and single-modal settings. The source code and trained models are available at: https://github.com/Amazingren/Point-CMAE.

Sharing Key Semantics in Transformer Makes Efficient Image Restoration

Image Restoration (IR), a classic low-level vision task, has witnessed significant advancements through deep models that effectively model global information. Notably, the Vision Transformers (ViTs) emergence has further propelled these advancements. When computing, the self-attention mechanism, a cornerstone of ViTs, tends to encompass all global cues, even those from semantically unrelated objects or regions. This inclusivity introduces computational inefficiencies, particularly noticeable with high input resolution, as it requires processing irrelevant information, thereby impeding efficiency. Additionally, for IR, it is commonly noted that small segments of a degraded image, particularly those closely aligned semantically, provide particularly relevant information to aid in the restoration process, as they contribute essential contextual cues crucial for accurate reconstruction. To address these challenges, we propose boosting IR's performance by sharing the key semantics via Transformer for IR (i.e., SemanIR) in this paper. Specifically, SemanIR initially constructs a sparse yet comprehensive key-semantic dictionary within each transformer stage by establishing essential semantic connections for every degraded patch. Subsequently, this dictionary is shared across all subsequent transformer blocks within the same stage. This strategy optimizes attention calculation within each block by focusing exclusively on semantically related components stored in the key-semantic dictionary. As a result, attention calculation achieves linear computational complexity within each window. Extensive experiments across 6 IR tasks confirm the proposed SemanIR's state-of-the-art performance, quantitatively and qualitatively showcasing advancements.

A Survey on Backbones for Deep Video Action Recognition

Action recognition is a key technology in building interactive metaverses. With the rapid development of deep learning, methods in action recognition have also achieved great advancement. Researchers design and implement the backbones referring to multiple standpoints, which leads to the diversity of methods and encountering new challenges. This paper reviews several action recognition methods based on deep neural networks. We introduce these methods in three parts: 1) Two-Streams networks and their variants, which, specifically in this paper, use RGB video frame and optical flow modality as input; 2) 3D convolutional networks, which make efforts in taking advantage of RGB modality directly while extracting different motion information is no longer necessary; 3) Transformer-based methods, which introduce the model from natural language processing into computer vision and video understanding. We offer objective sights in this review and hopefully provide a reference for future research.

Prompt When the Animal is: Temporal Animal Behavior Grounding with Positional Recovery Training

Temporal grounding is crucial in multimodal learning, but it poses challenges when applied to animal behavior data due to the sparsity and uniform distribution of moments. To address these challenges, we propose a novel Positional Recovery Training framework (Port), which prompts the model with the start and end times of specific animal behaviors during training. Specifically, Port enhances the baseline model with a Recovering part to predict flipped label sequences and align distributions with a Dual-alignment method. This allows the model to focus on specific temporal regions prompted by ground-truth information. Extensive experiments on the Animal Kingdom dataset demonstrate the effectiveness of Port, achieving an IoU@0.3 of 38.52. It emerges as one of the top performers in the sub-track of MMVRAC in ICME 2024 Grand Challenges.

SATO: Stable Text-to-Motion Framework

Is the Text to Motion model robust? Recent advancements in Text to Motion models primarily stem from more accurate predictions of specific actions. However, the text modality typically relies solely on pre-trained Contrastive Language-Image Pretraining (CLIP) models. Our research has uncovered a significant issue with the text-to-motion model: its predictions often exhibit inconsistent outputs, resulting in vastly different or even incorrect poses when presented with semantically similar or identical text inputs. In this paper, we undertake an analysis to elucidate the underlying causes of this instability, establishing a clear link between the unpredictability of model outputs and the erratic attention patterns of the text encoder module. Consequently, we introduce a formal framework aimed at addressing this issue, which we term the Stable Text-to-Motion Framework (SATO). SATO consists of three modules, each dedicated to stable attention, stable prediction, and maintaining a balance between accuracy and robustness trade-off. We present a methodology for constructing an SATO that satisfies the stability of attention and prediction. To verify the stability of the model, we introduced a new textual synonym perturbation dataset based on HumanML3D and KIT-ML. Results show that SATO is significantly more stable against synonyms and other slight perturbations while keeping its high accuracy performance.

SemiPL: A Semi-supervised Method for Event Sound Source Localization

In recent years, Event Sound Source Localization has been widely applied in various fields. Recent works typically relying on the contrastive learning framework show impressive performance. However, all work is based on large relatively simple datasets. It's also crucial to understand and analyze human behaviors (actions and interactions of people), voices, and sounds in chaotic events in many applications, e.g., crowd management, and emergency response services. In this paper, we apply the existing model to a more complex dataset, explore the influence of parameters on the model, and propose a semi-supervised improvement method SemiPL. With the increase in data quantity and the influence of label quality, self-supervised learning will be an unstoppable trend. The experiment shows that the parameter adjustment will positively affect the existing model. In particular, SSPL achieved an improvement of 12.2% cIoU and 0.56% AUC in Chaotic World compared to the results provided. The code is available at: https://github.com/ly245422/SSPL

HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition

Skeleton-based action recognition has gained considerable traction thanks to its utilization of succinct and robust skeletal representations. Nonetheless, current methodologies often lean towards utilizing a solitary backbone to model skeleton modality, which can be limited by inherent flaws in the network backbone. To address this and fully leverage the complementary characteristics of various network architectures, we propose a novel Hybrid Dual-Branch Network (HDBN) for robust skeleton-based action recognition, which benefits from the graph convolutional network's proficiency in handling graph-structured data and the powerful modeling capabilities of Transformers for global information. In detail, our proposed HDBN is divided into two trunk branches: MixGCN and MixFormer. The two branches utilize GCNs and Transformers to model both 2D and 3D skeletal modalities respectively. Our proposed HDBN emerged as one of the top solutions in the Multi-Modal Video Reasoning and Analyzing Competition (MMVRAC) of 2024 ICME Grand Challenge, achieving accuracies of 47.95% and 75.36% on two benchmarks of the UAV-Human dataset by outperforming most existing methods. Our code will be publicly available at: https://github.com/liujf69/ICMEW2024-Track10.

SFMViT: SlowFast Meet ViT in Chaotic World

The task of spatiotemporal action localization in chaotic scenes is a challenging task toward advanced video understanding. Paving the way with high-quality video feature extraction and enhancing the precision of detector-predicted anchors can effectively improve model performance. To this end, we propose a high-performance dual-stream spatiotemporal feature extraction network SFMViT with an anchor pruning strategy. The backbone of our SFMViT is composed of ViT and SlowFast with prior knowledge of spatiotemporal action localization, which fully utilizes ViT's excellent global feature extraction capabilities and SlowFast's spatiotemporal sequence modeling capabilities. Secondly, we introduce the confidence maximum heap to prune the anchors detected in each frame of the picture to filter out the effective anchors. These designs enable our SFMViT to achieve a mAP of 26.62% in the Chaotic World dataset, far exceeding existing models. Code is available at https://github.com/jfightyr/SlowFast-Meet-ViT.

MLP: Motion Label Prior for Temporal Sentence Localization in Untrimmed 3D Human Motions

In this paper, we address the unexplored question of temporal sentence localization in human motions (TSLM), aiming to locate a target moment from a 3D human motion that semantically corresponds to a text query. Considering that 3D human motions are captured using specialized motion capture devices, motions with only a few joints lack complex scene information like objects and lighting. Due to this character, motion data has low contextual richness and semantic ambiguity between frames, which limits the accuracy of predictions made by current video localization frameworks extended to TSLM to only a rough level. To refine this, we devise two novel label-prior-assisted training schemes: one embed prior knowledge of foreground and background to highlight the localization chances of target moments, and the other forces the originally rough predictions to overlap with the more accurate predictions obtained from the flipped start/end prior label sequences during recovery training. We show that injecting label-prior knowledge into the model is crucial for improving performance at high IoU. In our constructed TSLM benchmark, our model termed MLP achieves a recall of 44.13 at IoU@0.7 on the BABEL dataset and 71.17 on HumanML3D (Restore), outperforming prior works. Finally, we showcase the potential of our approach in corpus-level moment retrieval. Our source code is openly accessible at https://github.com/eanson023/mlp.

Point-In-Context: Understanding Point Cloud via In-Context Learning

With the emergence of large-scale models trained on diverse datasets, in-context learning has emerged as a promising paradigm for multitasking, notably in natural language processing and image processing. However, its application in 3D point cloud tasks remains largely unexplored. In this work, we introduce Point-In-Context (PIC), a novel framework for 3D point cloud understanding via in-context learning. We address the technical challenge of effectively extending masked point modeling to 3D point clouds by introducing a Joint Sampling module and proposing a vanilla version of PIC called Point-In-Context-Generalist (PIC-G). PIC-G is designed as a generalist model for various 3D point cloud tasks, with inputs and outputs modeled as coordinates. In this paradigm, the challenging segmentation task is achieved by assigning label points with XYZ coordinates for each category; the final prediction is then chosen based on the label point closest to the predictions. To break the limitation by the fixed label-coordinate assignment, which has poor generalization upon novel classes, we propose two novel training strategies, In-Context Labeling and In-Context Enhancing, forming an extended version of PIC named Point-In-Context-Segmenter (PIC-S), targeting improving dynamic context labeling and model training. By utilizing dynamic in-context labels and extra in-context pairs, PIC-S achieves enhanced performance and generalization capability in and across part segmentation datasets. PIC is a general framework so that other tasks or datasets can be seamlessly introduced into our PIC through a unified data format. We conduct extensive experiments to validate the versatility and adaptability of our proposed methods in handling a wide range of tasks and segmenting multi-datasets. Our PIC-S is capable of generalizing unseen datasets and performing novel part segmentation by customizing prompts.