Large language models (LLMs) have shown great potential in natural language processing tasks, but their application to machine translation (MT) remains challenging due to pretraining on English-centric data and the complexity of reinforcement learning from human feedback (RLHF). Direct Preference Optimization (DPO) has emerged as a simpler and more efficient alternative, but its performance depends heavily on the quality of preference data. To address this, we propose Confidence-Reward driven Preference Optimization (CRPO), a novel method that combines reward scores with model confidence to improve data selection for fine-tuning. CRPO selects challenging sentence pairs where the model is uncertain or underperforms, leading to more effective learning. While primarily designed for LLMs, CRPO also generalizes to encoder-decoder models like NLLB, demonstrating its versatility. Empirical results show that CRPO outperforms existing methods such as RS-DPO, RSO and MBR score in both translation accuracy and data efficiency.

Movie posters are not just decorative; they are meticulously designed to capture the essence of a movie, such as its genre, storyline, and tone/vibe. For decades, movie posters have graced cinema walls, billboards, and now our digital screens as a form of digital posters. Movie genre classification plays a pivotal role in film marketing, audience engagement, and recommendation systems. Previous explorations into movie genre classification have been mostly examined in plot summaries, subtitles, trailers and movie scenes. Movie posters provide a pre-release tantalizing glimpse into a film's key aspects, which can ignite public interest. In this paper, we presented the framework that exploits movie posters from a visual and textual perspective to address the multilabel movie genre classification problem. Firstly, we extracted text from movie posters using an OCR and retrieved the relevant embedding. Next, we introduce a cross-attention-based fusion module to allocate attention weights to visual and textual embedding. In validating our framework, we utilized 13882 posters sourced from the Internet Movie Database (IMDb). The outcomes of the experiments indicate that our model exhibited promising performance and outperformed even some prominent contemporary architectures.

We introduce VideoLISA, a video-based multimodal large language model designed to tackle the problem of language-instructed reasoning segmentation in videos. Leveraging the reasoning capabilities and world knowledge of large language models, and augmented by the Segment Anything Model, VideoLISA generates temporally consistent segmentation masks in videos based on language instructions. Existing image-based methods, such as LISA, struggle with video tasks due to the additional temporal dimension, which requires temporal dynamic understanding and consistent segmentation across frames. VideoLISA addresses these challenges by integrating a Sparse Dense Sampling strategy into the video-LLM, which balances temporal context and spatial detail within computational constraints. Additionally, we propose a One-Token-Seg-All approach using a specially designed token, enabling the model to segment and track objects across multiple frames. Extensive evaluations on diverse benchmarks, including our newly introduced ReasonVOS benchmark, demonstrate VideoLISA's superior performance in video object segmentation tasks involving complex reasoning, temporal understanding, and object tracking. While optimized for videos, VideoLISA also shows promising generalization to image segmentation, revealing its potential as a unified foundation model for language-instructed object segmentation.

Transformers have been successfully applied in the field of video-based 3D human pose estimation. However, the high computational costs of these video pose transformers (VPTs) make them impractical on resource-constrained devices. In this paper, we present a plug-and-play pruning-and-recovering framework, called Hourglass Tokenizer (HoT), for efficient transformer-based 3D human pose estimation from videos. Our HoT begins with pruning pose tokens of redundant frames and ends with recovering full-length tokens, resulting in a few pose tokens in the intermediate transformer blocks and thus improving the model efficiency. To effectively achieve this, we propose a token pruning cluster (TPC) that dynamically selects a few representative tokens with high semantic diversity while eliminating the redundancy of video frames. In addition, we develop a token recovering attention (TRA) to restore the detailed spatio-temporal information based on the selected tokens, thereby expanding the network output to the original full-length temporal resolution for fast inference. Extensive experiments on two benchmark datasets (i.e., Human3.6M and MPI-INF-3DHP) demonstrate that our method can achieve both high efficiency and estimation accuracy compared to the original VPT models. For instance, applying to MotionBERT and MixSTE on Human3.6M, our HoT can save nearly 50% FLOPs without sacrificing accuracy and nearly 40% FLOPs with only 0.2% accuracy drop, respectively. Our source code will be open-sourced.

Pre-trained vision transformers have strong representation benefits to various downstream tasks. Recently, many parameter-efficient fine-tuning (PEFT) methods have been proposed, and their experiments demonstrate that tuning only 1% of extra parameters could surpass full fine-tuning in low-data resource scenarios. However, these methods overlook the task-specific information when fine-tuning diverse downstream tasks. In this paper, we propose a simple yet effective method called "Salient Channel Tuning" (SCT) to leverage the task-specific information by forwarding the model with the task images to select partial channels in a feature map that enables us to tune only 1/8 channels leading to significantly lower parameter costs. Experiments outperform full fine-tuning on 18 out of 19 tasks in the VTAB-1K benchmark by adding only 0.11M parameters of the ViT-B, which is 780$\times$ fewer than its full fine-tuning counterpart. Furthermore, experiments on domain generalization and few-shot learning surpass other PEFT methods with lower parameter costs, demonstrating our proposed tuning technique's strong capability and effectiveness in the low-data regime.

The quadratic computational complexity to the number of tokens limits the practical applications of Vision Transformers (ViTs). Several works propose to prune redundant tokens to achieve efficient ViTs. However, these methods generally suffer from (i) dramatic accuracy drops, (ii) application difficulty in the local vision transformer, and (iii) non-general-purpose networks for downstream tasks. In this work, we propose a novel Semantic Token ViT (STViT), for efficient global and local vision transformers, which can also be revised to serve as backbone for downstream tasks. The semantic tokens represent cluster centers, and they are initialized by pooling image tokens in space and recovered by attention, which can adaptively represent global or local semantic information. Due to the cluster properties, a few semantic tokens can attain the same effect as vast image tokens, for both global and local vision transformers. For instance, only 16 semantic tokens on DeiT-(Tiny,Small,Base) can achieve the same accuracy with more than 100% inference speed improvement and nearly 60% FLOPs reduction; on Swin-(Tiny,Small,Base), we can employ 16 semantic tokens in each window to further speed it up by around 20% with slight accuracy increase. Besides great success in image classification, we also extend our method to video recognition. In addition, we design a STViT-R(ecover) network to restore the detailed spatial information based on the STViT, making it work for downstream tasks, which is powerless for previous token sparsification methods. Experiments demonstrate that our method can achieve competitive results compared to the original networks in object detection and instance segmentation, with over 30% FLOPs reduction for backbone. Code is available at http://github.com/changsn/STViT-R

Self-attention is powerful in modeling long-range dependencies, but it is weak in local finer-level feature learning. The performance of local self-attention (LSA) is just on par with convolution and inferior to dynamic filters, which puzzles researchers on whether to use LSA or its counterparts, which one is better, and what makes LSA mediocre. To clarify these, we comprehensively investigate LSA and its counterparts from two sides: \emph{channel setting} and \emph{spatial processing}. We find that the devil lies in the generation and application of spatial attention, where relative position embeddings and the neighboring filter application are key factors. Based on these findings, we propose the enhanced local self-attention (ELSA) with Hadamard attention and the ghost head. Hadamard attention introduces the Hadamard product to efficiently generate attention in the neighboring case, while maintaining the high-order mapping. The ghost head combines attention maps with static matrices to increase channel capacity. Experiments demonstrate the effectiveness of ELSA. Without architecture / hyperparameter modification, drop-in replacing LSA with ELSA boosts Swin Transformer \cite{swin} by up to +1.4 on top-1 accuracy. ELSA also consistently benefits VOLO \cite{volo} from D1 to D5, where ELSA-VOLO-D5 achieves 87.2 on the ImageNet-1K without extra training images. In addition, we evaluate ELSA in downstream tasks. ELSA significantly improves the baseline by up to +1.9 box Ap / +1.3 mask Ap on the COCO, and by up to +1.9 mIoU on the ADE20K. Code is available at \url{https://github.com/damo-cv/ELSA}.

Unsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations. Most existing methods are bottom-up approaches that try to group pixels into regions based on their visual cues or certain predefined rules. As a result, it is difficult for these bottom-up approaches to generate fine-grained semantic segmentation when coming to complicated scenes with multiple objects and some objects sharing similar visual appearance. In contrast, we propose the first top-down unsupervised semantic segmentation framework for fine-grained segmentation in extremely complicated scenarios. Specifically, we first obtain rich high-level structured semantic concept information from large-scale vision data in a self-supervised learning manner, and use such information as a prior to discover potential semantic categories presented in target datasets. Secondly, the discovered high-level semantic categories are mapped to low-level pixel features by calculating the class activate map (CAM) with respect to certain discovered semantic representation. Lastly, the obtained CAMs serve as pseudo labels to train the segmentation module and produce final semantic segmentation. Experimental results on multiple semantic segmentation benchmarks show that our top-down unsupervised segmentation is robust to both object-centric and scene-centric datasets under different semantic granularity levels, and outperforms all the current state-of-the-art bottom-up methods. Our code is available at \url{https://github.com/damo-cv/TransFGU}.

Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spatial and temporal relationships. However, those works ignore the fact that it is an inverse problem where multiple feasible solutions (i.e., hypotheses) exist. To relieve this limitation, we propose a Multi-Hypothesis Transformer (MHFormer) that learns spatio-temporal representations of multiple plausible pose hypotheses. In order to effectively model multi-hypothesis dependencies and build strong relationships across hypothesis features, the task is decomposed into three stages: (i) Generate multiple initial hypothesis representations; (ii) Model self-hypothesis communication, merge multiple hypotheses into a single converged representation and then partition it into several diverged hypotheses; (iii) Learn cross-hypothesis communication and aggregate the multi-hypothesis features to synthesize the final 3D pose. Through the above processes, the final representation is enhanced and the synthesized pose is much more accurate. Extensive experiments show that MHFormer achieves state-of-the-art results on two challenging datasets: Human3.6M and MPI-INF-3DHP. Without bells and whistles, its performance surpasses the previous best result by a large margin of 3% on Human3.6M. Code and models are available at https://github.com/Vegetebird/MHFormer.

A novel deep neural network training paradigm that exploits the conjoint information in multiple heterogeneous sources is proposed. Specifically, in a RGB-D based action recognition task, it cooperatively trains a single convolutional neural network (named c-ConvNet) on both RGB visual features and depth features, and deeply aggregates the two kinds of features for action recognition. Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power of the deeply learned features and weakens the undesired modality discrepancy by jointly optimizing a ranking loss and a softmax loss for both homogeneous and heterogeneous modalities. The ranking loss consists of intra-modality and cross-modality triplet losses, and it reduces both the intra-modality and cross-modality feature variations. Furthermore, the correlations between RGB and depth data are embedded in the c-ConvNet, and can be retrieved by either of the modalities and contribute to the recognition in the case even only one of the modalities is available. The proposed method was extensively evaluated on two large RGB-D action recognition datasets, ChaLearn LAP IsoGD and NTU RGB+D datasets, and one small dataset, SYSU 3D HOI, and achieved state-of-the-art results.